© 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. 42342
    Prev
    Next
    INDEX
    Explanations

    a lot

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

    alerts lasted, sharing system, quotation marks

    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
    აცია
    0.47
     lact
    0.46
     Yaj
    0.42
     soda
    0.42
     *>
    0.42
     Benz
    0.40
     Millions
    0.40
    នៃ
    0.39
    pyrazine
    0.39
     ！
    0.39
    POSITIVE LOGITS
    ிற்க
    0.51
     मध्यप्रदेश
    0.47
    thom
    0.47
    msgs
    0.46
    济
    0.46
    ipherals
    0.46
     świet
    0.45
    ᱘
    0.45
    fighting
    0.45
    狼
    0.45
    Activations Density 0.000%

    No Known Activations