© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 25770
    Prev
    Next
    INDEX
    Explanations

    court calendar

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

    The neuron is triggered by CamelCase or multi-part code identifiers (e.g. class, method, or property names) in source‐like 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_34/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
    %!
    -0.98
    %;">
    -0.97
     ?
    -0.93
    dsquared
    -0.91
    ukų
    -0.91
     aquellos
    -0.87
     their
    -0.86
     aquella
    -0.85
     what
    -0.84
    nance
    -0.84
    POSITIVE LOGITS
    малар
    1.10
    endregion
    1.01
     franquicia
    0.96
    だからこそ
    0.96
    particularly
    0.96
    もありますが
    0.96
    についても
    0.95
    this
    0.95
    ;,
    0.94
     ส์
    0.93
    Activations Density 0.001%

    No Known Activations