© 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. 225439
    Prev
    Next
    INDEX
    Explanations

    decided, moulds, lifespan, tally

    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
    benzoimidazol
    0.50
    evoluzione
    0.49
    وقال
    0.47
    걸
    0.46
    KAN
    0.46
    چ
    0.46
    ρώ
    0.45
    PRODUCT
    0.45
    denomination
    0.45
    በ
    0.45
    POSITIVE LOGITS
    </code>
    0.51
    谑
    0.49
     sust
    0.48
    ip
    0.48
     Kv
    0.48
     Ks
    0.48
     transporter
    0.47
    as
    0.47
     Prim
    0.47
     JAN
    0.46
    Activations Density 0.000%

    No Known Activations