© 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. 194683
    Prev
    Next
    INDEX
    Explanations

    floor mats

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

    SQL query syntax

    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
    dR
    0.45
    戾
    0.43
    CITATION
    0.42
     बला
    0.42
     __
    0.41
     מדי
    0.41
     pev
    0.41
    ur
    0.41
    -{\
    0.41
     來
    0.41
    POSITIVE LOGITS
    ッカー
    0.50
     প্রভাস
    0.49
    ക്കിയി
    0.48
    ێک
    0.45
    વણી
    0.44
     Greenberg
    0.43
     walter
    0.43
    Walter
    0.42
     networked
    0.42
     reapp
    0.42
    Activations Density 0.002%

    No Known Activations