© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 212588
    Prev
    Next
    INDEX
    Explanations

    call, Pope, label, rating, strategies, pack, Shi

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

    the primary or leading descriptor

    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
    永远
    0.46
    सैन
    0.45
     аутох
    0.44
     Surge
    0.44
     третий
    0.44
    娅
    0.44
    癥
    0.44
    andus
    0.43
    佘
    0.43
     هلا
    0.43
    POSITIVE LOGITS
     conductance
    0.46
     laminate
    0.45
    łości
    0.44
     polycarbonate
    0.44
     liquid
    0.43
     coolant
    0.43
     as
    0.42
     laminated
    0.42
     від
    0.42
     cellulose
    0.42
    Activations Density 0.000%

    No Known Activations