© 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. 17500
    Prev
    Next
    INDEX
    Explanations

    black shoes, apparel, and appliances

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

    athletic footwear style

    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
    <i>
    0.50
    aba
    0.47
    Су
    0.47
    fort
    0.46
    С
    0.46
    template
    0.45
    us
    0.43
    an
    0.41
    Template
    0.40
    o
    0.40
    POSITIVE LOGITS
     ব্যাগ
    0.50
     velcro
    0.48
     बैग
    0.46
     బ్యాంకు
    0.46
     scarves
    0.46
     костю
    0.45
     μαύ
    0.45
     σα
    0.45
     bike
    0.45
     청바
    0.45
    Activations Density 0.001%

    No Known Activations