© 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. 47999
    Prev
    Next
    INDEX
    Explanations

    code comments and documentation

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

    This neuron is highly sensitive to numeric tokens (literal numbers and numeric-like strings) in the 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
    LessThan
    -0.74
     Augsburg
    -0.73
     thương
    -0.70
    metido
    -0.70
    ℰ
    -0.69
     center
    -0.68
     Bret
    -0.68
     SCC
    -0.67
    FileInput
    -0.66
    Ꮃ
    -0.66
    POSITIVE LOGITS
    формация
    0.79
     profonda
    0.70
     Thra
    0.66
    piv
    0.65
     zb
    0.65
    ኣ
    0.65
     veille
    0.65
    nitten
    0.64
    hin
    0.64
    cul
    0.63
    Activations Density 0.077%

    No Known Activations