© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130171
    Prev
    Next
    INDEX
    Explanations

    The neuron responds to the names of modules, packages, or directories in import/include paths.

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

    import, Anatomy, peer, The, An, I

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     there
    -1.28
     today
    -1.09
     instead
    -1.06
    に来て
    -1.02
     on
    -1.01
     in
    -0.99
     necesitan
    -0.95
     unless
    -0.95
     to
    -0.94
     if
    -0.94
    POSITIVE LOGITS
     consiste
    1.24
    おわりに
    1.16
     nutz
    1.13
     recha
    1.07
     caché
    1.05
    Уже
    1.03
     engend
    1.02
     discu
    1.02
     به‌
    1.02
     violen
    1.01
    Activations Density 0.003%

    No Known Activations