© 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. 228968
    Prev
    Next
    INDEX
    Explanations

    court, law, persons

    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
    大胆
    0.50
    रासत
    0.44
    因为它
    0.44
    ুদের
    0.44
     Volumen
    0.44
     Sistem
    0.43
     Genealogical
    0.43
    䈉
    0.43
    !]
    0.42
    楫
    0.42
    POSITIVE LOGITS
     бя
    0.48
     spanning
    0.48
    RENDER
    0.47
     түр
    0.46
     суток
    0.46
     туристи
    0.43
     ан
    0.43
     кра
    0.43
     роз
    0.42
     пон
    0.42
    Activations Density 0.000%

    No Known Activations