© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 11451
    Prev
    Next
    INDEX
    Explanations

    program code and web addresses

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

    method or function names in programming code, particularly those related to redirection, rendering, or canvas operations.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    This neuron responds to code identifiers for function or method calls (e.g. Redirect, canvas, Write, 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_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
    擱
    -1.41
     автомобиля
    -1.39
     TABLES
    -1.38
    e
    -1.36
     skapa
    -1.35
     stesso
    -1.34
     gratuitas
    -1.34
    A
    -1.34
     aéreas
    -1.34
     kunna
    -1.32
    POSITIVE LOGITS
    </em>
    1.97
    夲
    1.69
     afla
    1.56
     aftermath
    1.49
     to
    1.45
    🗸
    1.42
    cauciones
    1.38
     Extending
    1.37
     lieu
    1.36
     lediglich
    1.36
    Activations Density 0.000%

    No Known Activations