© 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. 82476
    Prev
    Next
    INDEX
    Explanations

    location, json, error

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

    This neuron detects numeric sequences (digits) such as literal numbers in code or URLs.

    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
    happ
    -0.78
     Sound
    -0.77
    vollen
    -0.75
     год
    -0.73
    bav
    -0.70
    %</
    -0.70
    apte
    -0.69
     Ensino
    -0.69
    tito
    -0.69
    ZD
    -0.68
    POSITIVE LOGITS
     vicinity
    1.09
    geometry
    0.92
    Geometry
    0.92
     establishment
    0.88
     place
    0.85
     ICH
    0.82
    types
    0.81
    PENDAHULUAN
    0.78
    зыва
    0.78
    vic
    0.77
    Activations Density 0.015%

    No Known Activations