© 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. 141924
    Prev
    Next
    INDEX
    Explanations

    identifying categories and related concepts

    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
     Sandals
    0.48
    أي
    0.42
     Многие
    0.41
     своим
    0.41
     চিন্তা
    0.40
    <blockquote>
    0.40
     Solomon
    0.40
     Interior
    0.39
    navigationLinks
    0.39
    鄯
    0.39
    POSITIVE LOGITS
     suur
    0.49
     när
    0.44
    FORMAN
    0.44
    フォー
    0.44
     cuando
    0.43
     fác
    0.43
     määr
    0.43
     bestow
    0.43
     hau
    0.42
     quando
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.