© 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. 188992
    Prev
    Next
    INDEX
    Explanations

    slots, comfort, small, apply, welcomed

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

    suggest strategies

    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
    シス
    0.52
    必要な
    0.50
    看看
    0.50
    ཁ
    0.47
    時には
    0.46
    Interstitial
    0.46
     Onda
    0.46
    '
    0.44
    പ്ര
    0.44
    woocommerce
    0.44
    POSITIVE LOGITS
    सायटी
    0.50
    izr
    0.42
     unmittel
    0.42
     hier
    0.41
     stammt
    0.41
     vik
    0.41
    ettek
    0.41
     zwe
    0.40
    SEQ
    0.40
    ix
    0.40
    Activations Density 0.000%

    No Known Activations