© 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. 10-GEMMASCOPE-RES-131K
    7. 103220
    Prev
    Next
    INDEX
    Explanations

    all indices and comprehensive coverage

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

    The neuron flags tokens that look like programming identifiers or code symbols—e.g. method/property names, JSON attribute names, CamelCase or underscore-style identifiers.

    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
    脔
    -2.78
     This
    -2.75
     is
    -2.72
    咴
    -2.67
    ."
    -2.44
     такая
    -2.36
    擱
    -2.36
    綸
    -2.30
     These
    -2.28
     сили
    -2.28
    POSITIVE LOGITS
    1
    2.77
    пъл
    2.39
    0
    2.30
    的那个
    2.22
     sorprend
    2.20
     Improves
    2.14
     mají
    2.11
    和你
    2.06
    n
    2.05
    ままで
    2.02
    Activations Density 0.001%

    No Known Activations