© 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. 157638
    Prev
    Next
    INDEX
    Explanations

    labor law

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

    impossible, historically, very

    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
     লা
    0.52
    ാവ്
    0.50
    どんな
    0.49
     딸
    0.48
     전문가
    0.48
     புற்று
    0.48
    ೆ
    0.48
     मतदारसं
    0.47
    聞いて
    0.47
     Европей
    0.47
    POSITIVE LOGITS
    itative
    0.44
     impeachment
    0.43
     GmbH
    0.43
     Oxf
    0.43
     sö
    0.42
    力的
    0.42
     Implement
    0.42
     Sharing
    0.42
     №
    0.42
    0.42
    Activations Density 0.000%

    No Known Activations