© 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. 39090
    Prev
    Next
    INDEX
    Explanations

    Hunting Trips, Effect on

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

    This neuron responds to structural code tokens—especially generics and type‐constraint syntax (e.g. angle brackets, colons, the “where” keyword, and curly braces).

    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
     vow
    -1.00
     Få
    -0.98
     Nå
    -0.97
     AKA
    -0.96
     aka
    -0.96
    endphp
    -0.96
    ingual
    -0.95
    랬
    -0.92
     Ahora
    -0.92
    льному
    -0.92
    POSITIVE LOGITS
     that
    1.51
     necessários
    1.37
     poderão
    1.24
     preferências
    1.14
     adicionais
    1.14
     if
    1.10
     perfeitamente
    1.07
     geprü
    1.05
    ).
    1.05
     Crowe
    1.03
    Activations Density 0.002%

    No Known Activations