© 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. 71760
    Prev
    Next
    INDEX
    Explanations

    compressed air, exclusive content, important topics, reason

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

    blocked, rejected

    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
     лигасы
    0.54
    ೂರ್ವ
    0.48
    按钮
    0.48
    粥
    0.48
     мл
    0.46
    最小
    0.46
    ccbp
    0.46
    gtk
    0.46
    тивная
    0.45
    边
    0.45
    POSITIVE LOGITS
     sint
    0.48
    وجه
    0.48
     daylight
    0.47
    یف
    0.47
    al
    0.47
     deple
    0.46
     dà
    0.46
    माण
    0.45
     מה
    0.44
     termite
    0.44
    Activations Density 0.001%

    No Known Activations