© 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. 234528
    Prev
    Next
    INDEX
    Explanations

    fire, response, inflammatory, never end

    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
     defaultdict
    0.46
     Ornament
    0.44
    arit
    0.44
     روایت
    0.44
     πάν
    0.43
     тео
    0.43
    虻
    0.43
    僉
    0.43
     rounding
    0.42
    Asalamualaikum
    0.41
    POSITIVE LOGITS
    cu
    0.52
    cuda
    0.46
    代引き
    0.45
    cystic
    0.45
    GeV
    0.44
     ಬೆ
    0.44
    genstein
    0.44
    CK
    0.43
    .*
    0.43
    TABLE
    0.43
    Activations Density 0.000%

    No Known Activations