© 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. 23188
    Prev
    Next
    INDEX
    Explanations

    section following numbers or letters

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

    section headings

    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
     Morin
    0.47
    ;
    0.46
    ili
    0.46
    |
    0.46
    ii
    0.44
    quad
    0.43
     Cochran
    0.43
    despite
    0.43
    ahay
    0.43
    ||
    0.43
    POSITIVE LOGITS
    Parameter
    0.55
    Გ
    0.53
    Ყ
    0.52
     inicial
    0.51
    ালক
    0.51
    াল্ড
    0.48
    Ფ
    0.48
    駋
    0.47
    Კ
    0.47
     ተጨማሪ
    0.47
    Activations Density 0.000%

    No Known Activations