© 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. 22-GEMMASCOPE-RES-131K
    7. 129261
    Prev
    Next
    INDEX
    Explanations

    The neuron is triggered by numeric digit tokens (e.g., the individual digits in JSON number literals, especially in coordinate values).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    place names or proper nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     eene
    -1.33
    #########
    -1.16
     bluse
    -1.14
     Início
    -1.14
     soyez
    -1.13
    hogs
    -1.13
    🧍
    -1.13
     miſ
    -1.13
     Informações
    -1.12
    
    -1.11
    POSITIVE LOGITS
    7
    1.04
    テーマ
    0.98
    ;
    0.95
     maior
    0.92
     newest
    0.92
    postalCode
    0.91
    el
    0.90
    enumi
    0.89
     почина
    0.88
    Олег
    0.88
    Activations Density 0.000%

    No Known Activations