© 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. 122017
    Prev
    Next
    INDEX
    Explanations

    Polish, site, information, independently, liquid

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

    detail followed by colon

    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
    CCOCC
    0.62
    <unused2018>
    0.62
     அரசிய
    0.59
     ಸಂಖ್ಯ
    0.55
     ఆరోగ
    0.54
     автомобиль
    0.54
     району
    0.54
    ไซต์
    0.54
    <unused229>
    0.53
     sağlık
    0.52
    POSITIVE LOGITS
    E
    0.59
    /
    0.58
    );
    0.56
    ed
    0.55
     neg
    0.50
     him
    0.49
    ,
    0.49
    V
    0.49
     proxy
    0.48
    e
    0.48
    Activations Density 0.000%

    No Known Activations