© 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. 229037
    Prev
    Next
    INDEX
    Explanations

    site .certified .our perceptionsto providestill respectingresult if

    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
    gruppen
    0.46
     pol
    0.46
     (
    0.45
     tabletop
    0.45
    ten
    0.44
    berts
    0.44
     pen
    0.44
     Zoll
    0.43
    tbl
    0.42
     majeure
    0.42
    POSITIVE LOGITS
    ೆಯಲ್ಲಿ
    0.60
     или
    0.57
    讧
    0.57
     хими
    0.56
    強い
    0.55
    ની
    0.55
     いや
    0.54
    কেমিক্যাল
    0.54
    変更
    0.53
    UpperCase
    0.52
    Activations Density 0.000%

    No Known Activations