© 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. 126397
    Prev
    Next
    INDEX
    Explanations

    features and items

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

    drive those, Delta, Wipe, capturing

    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
    منی
    0.53
    கடந்த
    0.51
    फूल
    0.50
    /
    0.47
    owna
    0.47
    अंत
    0.46
     vicepresidente
    0.46
    एसपी
    0.45
     Tekn
    0.45
     gyn
    0.45
    POSITIVE LOGITS
    耐久
    0.49
     ем
    0.47
     функ
    0.46
    見
    0.44
    ъм
    0.44
    動物
    0.44
    طم
    0.44
     surjective
    0.44
    u
    0.44
    '"
    0.42
    Activations Density 0.000%

    No Known Activations