© 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. 10-GEMMASCOPE-RES-131K
    7. 8287
    Prev
    Next
    INDEX
    Explanations

    programming library keywords

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

    This neuron fires on code tokens that are parts of CamelCase or uppercase identifiers (e.g. class, method, or type names).

    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
     kellett
    -1.59
    tplatz
    -1.44
    barcelona
    -1.42
    (!__
    -1.35
    螃
    -1.34
    onden
    -1.30
    itieren
    -1.29
    Thông
    -1.29
     файла
    -1.26
    Thành
    -1.25
    POSITIVE LOGITS
     only
    1.73
     like
    1.68
    (
    1.62
    but
    1.51
    only
    1.43
     two
    1.41
     it
    1.39
     what
    1.38
    "
    1.35
    er
    1.34
    Activations Density 0.022%

    No Known Activations