© 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. 112227
    Prev
    Next
    INDEX
    Explanations

    Lord Shiva

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

    per, motion, or quantity

    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
    .
    0.54
     первом
    0.50
    ansas
    0.50
     burada
    0.46
    não
    0.46
    qe
    0.45
    .";
    0.45
    /
    0.44
    </td>
    0.44
    west
    0.44
    POSITIVE LOGITS
    ர்ஸ்
    0.48
    手臂
    0.46
    ദ്ധതി
    0.45
     *}(
    0.44
    幼稚
    0.43
    襁
    0.42
    किया
    0.41
     राघव
    0.41
    protective
    0.40
    FindFileData
    0.40
    Activations Density 0.000%

    No Known Activations