© 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. 130471
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on multiword code identifiers (class, type, or method names) written in camelCase or PascalCase.

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

    programming types and classes

    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
     '>=
    -2.41
    𝖕
    -2.30
     или
    -2.25
    \
    -2.25
     \
    -2.25
    At
    -2.23
     With
    -2.20
    But
    -2.20
     Why
    -2.16
    In
    -2.14
    POSITIVE LOGITS
     глазах
    2.42
     белом
    2.38
    沵
    2.20
    薮
    2.19
    癭
    2.17
    lgari
    2.14
    ₶
    2.13
    鹮
    2.11
     stockfoto
    2.05
     кухне
    2.05
    Activations Density 0.032%

    No Known Activations