© 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. 34525
    Prev
    Next
    INDEX
    Explanations

    quantitative method harsh way

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

    aiming to

    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
    𝒂
    0.50
     μετά
    0.50
     夏
    0.48
     apa
    0.47
     μέ
    0.47
     joueur
    0.46
     atau
    0.46
     (
    0.46
     berth
    0.46
     stroke
    0.45
    POSITIVE LOGITS
    لق
    0.52
    sigs
    0.50
    ن
    0.49
    囫
    0.49
    ln
    0.47
    ಲ್ಲಿ
    0.47
    чний
    0.47
    surfing
    0.46
    nagy
    0.46
    dí
    0.46
    Activations Density 0.000%

    No Known Activations