© 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. 34-GEMMASCOPE-RES-131K
    7. 117784
    Prev
    Next
    INDEX
    Explanations

    Factors influencing

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

    The neuron is attuned to numeric tokens—dates, figures, and other number sequences (including years, dollar amounts, and statistics).

    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
    незон
    -0.72
     towards
    -0.71
    trero
    -0.71
     totalCount
    -0.70
     שירות
    -0.69
    ลักษ
    -0.68
    Der
    -0.66
    topes
    -0.66
     appalled
    -0.66
    Detection
    -0.65
    POSITIVE LOGITS
    ustomed
    0.79
     GDP
    0.79
    letka
    0.76
    ┮
    0.75
    ակ
    0.75
    țiuni
    0.73
     ionic
    0.73
     XVI
    0.72
    şme
    0.71
     BASE
    0.71
    Activations Density 0.015%

    No Known Activations