© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 10849
    Prev
    Next
    INDEX
    Explanations

    code comments and identifiers

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

    The neuron fires on numerical literals (digit‐only tokens) typically found in code, documentation, or markup contexts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    lampu
    -1.03
    russ
    -1.02
    Conseils
    -1.00
     Ży
    -0.98
     monaster
    -0.93
    cropping
    -0.92
     muñecas
    -0.91
     camisa
    -0.91
    stande
    -0.90
     cioc
    -0.90
    POSITIVE LOGITS
     веке
    0.95
    ATHER
    0.87
    гада
    0.82
    ACTION
    0.82
     into
    0.81
     from
    0.81
    ssid
    0.81
    Specificity
    0.79
     розо
    0.79
     exchangers
    0.79
    Activations Density 0.000%

    No Known Activations