© 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. 53607
    Prev
    Next
    INDEX
    Explanations

    quant

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

    marinade

    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
     Künstler
    0.49
     Tigers
    0.48
    抑
    0.48
     Dances
    0.47
     lyrical
    0.47
     Glitter
    0.46
     Baseball
    0.46
    قدر
    0.46
     Spiele
    0.45
     tigers
    0.44
    POSITIVE LOGITS
    ayana
    0.41
     공급
    0.41
    ادية
    0.40
    cg
    0.39
    datatype
    0.39
     quant
    0.39
     multil
    0.38
    ^{-
    0.38
    dit
    0.38
    Mort
    0.38
    Activations Density 0.000%

    No Known Activations