© 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. 249595
    Prev
    Next
    INDEX
    Explanations

    allow you, transformed into, circumstances, from his, travel to, index, Should a, capable of

    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
    mq
    0.53
    వో
    0.46
    <code>
    0.46
    /**
    0.45
    <?
    0.45
    isDisabled
    0.45
     extravaganza
    0.44
    <blockquote>
    0.44
    main
    0.44
    ON
    0.44
    POSITIVE LOGITS
     আলোক
    0.53
     Sedona
    0.50
     zumindest
    0.49
     anta
    0.46
     البع
    0.46
     Boż
    0.46
     امشي
    0.46
     conformal
    0.45
     erne
    0.45
     цю
    0.45
    Activations Density 0.000%

    No Known Activations