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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 98403
    Prev
    Next
    INDEX
    Explanations

    just to

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

    The neuron fires strongly on common emphatic adverbs (e.g. “just,” “ever”), i.e. intensifiers that add emphasis.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    を
    -1.60
    や
    -1.57
     also
    -1.56
    などを
    -1.50
    などが
    -1.50
    が
    -1.43
    は
    -1.42
     these
    -1.41
    それに
    -1.31
    も
    -1.30
    POSITIVE LOGITS
    為に
    2.08
    corrhi
    1.96
    際に
    1.72
    久し
    1.70
    diseño
    1.70
    感じです
    1.70
    ようになります
    1.69
    に入れ
    1.69
    感じで
    1.61
    気がします
    1.59
    Activations Density 0.089%

    No Known Activations