© 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. 59440
    Prev
    Next
    INDEX
    Explanations

    compound terms

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

    overwork. participate hints role

    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
     प्रिय
    0.47
    이제
    0.47
    ждение
    0.46
    Unh
    0.46
     தின
    0.45
    Pivot
    0.45
    潾
    0.44
    ля
    0.43
     फीसदी
    0.43
     모두
    0.43
    POSITIVE LOGITS
    ;
    0.54
    ,
    0.48
     it
    0.46
     (
    0.46
    -,
    0.45
    ‖
    0.44
     slightly
    0.43
     evaluate
    0.43
     −
    0.43
     -
    0.42
    Activations Density 0.000%

    No Known Activations