© 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. 90993
    Prev
    Next
    INDEX
    Explanations

    permitted provided governed

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

    This neuron fires on tokens containing numeric digits (e.g., version numbers, function argument names with numbers, numeric literals).

    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
    مین
    -0.92
    ÉR
    -0.90
    IBinder
    -0.87
    litis
    -0.85
    +=(
    -0.85
    isdir
    -0.84
     "<<
    -0.83
    Více
    -0.80
    nehå
    -0.79
    ofib
    -0.79
    POSITIVE LOGITS
    increments
    0.96
    presas
    0.93
     id
    0.91
     Zjednoc
    0.82
    Consumed
    0.81
     tributes
    0.78
     indicative
    0.77
     prolong
    0.77
    普通的
    0.76
     commentary
    0.75
    Activations Density 0.003%

    No Known Activations