© 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. 116568
    Prev
    Next
    INDEX
    Explanations

    responsibilities, access, text, took, Nov

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

    first explaining statements

    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
    difficult
    0.46
    केशन
    0.46
    v
    0.46
    Payout
    0.45
    लग
    0.44
    वायर
    0.44
     algum
    0.43
    pian
    0.42
     Refunds
    0.42
    ডিং
    0.41
    POSITIVE LOGITS
     আপাত
    0.46
     cadenas
    0.43
     Veh
    0.42
     তারা
    0.42
     Spielen
    0.41
     droit
    0.41
     geodesic
    0.41
     잠
    0.40
     Horizontal
    0.39
     ಇಲ್ಲಿ
    0.39
    Activations Density 0.002%

    No Known Activations