© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 70972
    Prev
    Next
    INDEX
    Explanations

    concepts and their methods

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

    The neuron is primarily sensitive to key content nouns (i.e. topic-defining words) in the text.

    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
     industrie
    -1.17
    ❌
    -1.16
    wich
    -1.07
    ആ
    -1.06
    ℟
    -1.05
    Ẓ
    -1.05
     exacte
    -1.04
    chi
    -1.04
    од
    -1.03
    zij
    -1.03
    POSITIVE LOGITS
     also
    1.61
     would
    1.48
     definitely
    1.22
     probably
    1.17
     certainly
    1.15
     then
    1.09
     shouldn
    1.05
     might
    1.03
     Also
    1.03
     também
    1.02
    Activations Density 0.045%

    No Known Activations