© 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. 7391
    Prev
    Next
    INDEX
    Explanations

    contact information or structure

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

    ch words

    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
    曙
    0.39
    ষধ
    0.39
     retardation
    0.37
     अनावश्यक
    0.35
    NuGetPackage
    0.35
    傆
    0.34
     glycogen
    0.34
    ())))
    0.34
     sprayer
    0.33
    ىن
    0.33
    POSITIVE LOGITS
    </h4>
    0.66
    <h4>
    0.59
    <h5>
    0.50
    <h6>
    0.44
    rated
    0.41
    ';
    0.39
    ";
    0.39
    ”;
    0.39
    **/
    0.38
    #######
    0.38
    Activations Density 0.000%

    No Known Activations