© 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. 8658
    Prev
    Next
    INDEX
    Explanations

    end of html document

    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
     deductible
    0.35
     अल्कोहल
    0.34
     vaš
    0.34
    ಬ್ಬಳ್ಳಿ
    0.34
    债
    0.34
     involuntary
    0.33
    ascus
    0.33
    ക്കിയത്
    0.33
     cosmetology
    0.33
    PageComponent
    0.33
    POSITIVE LOGITS
    つま
    0.39
    s
    0.39
     Parisian
    0.38
    yl
    0.37
    μένο
    0.36
    tar
    0.34
     Ры
    0.34
     пон
    0.34
    さに
    0.34
     Loire
    0.34
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.