© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 71630
    Prev
    Next
    INDEX
    Explanations

    degree of intensity

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects degree-intensifying modifiers—adjectives or adverbs that amplify magnitude or extent (e.g. “pretty,” “huge,” “fairly,” “quite a lot of,” “relatively,” “big”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    phrases that use degree modifiers to intensify adjectives, signaling notable magnitude, frequency, difficulty, or commonness.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    intensifying adverbs (like "pretty," "fairly," "quite") that modify adjectives describing size or degree.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Such
    -1.27
    かもしれない
    -1.27
     pratiquement
    -1.25
    入れた
    -1.24
     Notably
    -1.23
    価格は
    -1.22
     zugleich
    -1.20
    怎么可能
    -1.20
     such
    -1.18
    İK
    -1.18
    POSITIVE LOGITS
      【
    1.53
     نیز
    1.46
     довольно
    1.34
     philosophie
    1.34
    \}\
    1.34
    \}=
    1.30
     bastante
    1.27
    ądz
    1.24
     경우
    1.23
    }\
    1.23
    Activations Density 0.134%

    No Known Activations