© 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. 226123
    Prev
    Next
    INDEX
    Explanations

    precaution is important

    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
     Siempre
    0.46
     अक्सर
    0.46
    ※
    0.45
    磯
    0.44
    枇
    0.44
    銠
    0.44
    야
    0.43
    эр
    0.42
     кеңселер
    0.42
     чаще
    0.42
    POSITIVE LOGITS
    astă
    0.45
    language
    0.43
     attaques
    0.42
    it
    0.42
    dorff
    0.41
     damals
    0.41
     हमने
    0.41
    ardan
    0.40
    dans
    0.40
     hỗn
    0.40
    Activations Density 0.000%

    No Known Activations