© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34023
    Prev
    Next
    INDEX
    Explanations

    code imports and declarations

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

    This neuron fires on tokens that start code statements (i.e. the leading identifier or keyword at the beginning of a line of code).

    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
    breviations
    -1.21
    なんですね
    -1.14
     Método
    -1.03
    ẩ
    -1.02
    bree
    -1.02
     серпня
    -1.02
    êmes
    -1.01
     hydrauli
    -1.01
    ꪻ
    -1.00
    ┿
    -0.99
    POSITIVE LOGITS
    ↵↵
    1.21
     hauptsächlich
    0.99
     zuerst
    0.98
    による
    0.96
     идея
    0.93
    了一些
    0.93
    Buna
    0.91
     weitgehend
    0.88
     основ
    0.88
     basic
    0.88
    Activations Density 0.001%

    No Known Activations