© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 45364
    Prev
    Next
    INDEX
    Explanations

    public declarations in code

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

    This neuron fires on code‐declaration keywords and return‐type identifiers (e.g. “public,” “class,” “String,” “int,” “return,” etc.)

    oai_token-act-pair · o4-miniTriggered 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
     \"
    -1.74
     ì
    -1.50
    が無い
    -1.49
    exemple
    -1.48
    hender
    -1.48
    神
    -1.48
     無地
    -1.47
    Gön
    -1.45
    幾天
    -1.43
    が使
    -1.41
    POSITIVE LOGITS
     on
    2.39
    ,
    1.66
     or
    1.55
     with
    1.53
     as
    1.47
    :
    1.40
    האם
    1.39
     it
    1.38
     (
    1.31
    bowler
    1.28
    Activations Density 0.002%

    No Known Activations