© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 162379
    Prev
    Next
    INDEX
    Explanations

    Cosmetics, intense, fee, drugs, value

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

    parts, timesheet, cost, peace

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     uży
    0.49
    Although
    0.46
    种种
    0.45
    {
    0.43
    一带
    0.42
    ہ
    0.42
    广泛
    0.42
     kullanıl
    0.41
     található
    0.41
    ലീസ്
    0.41
    POSITIVE LOGITS
    uot
    0.52
     積
    0.52
    uttu
    0.50
     motors
    0.46
     vapors
    0.46
     жидкости
    0.46
    ulit
    0.45
    စျေး
    0.45
     saver
    0.45
    prechen
    0.44
    Activations Density 0.003%

    No Known Activations