© 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. 125197
    Prev
    Next
    INDEX
    Explanations

    alphabetical order, shop Amazon

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

    static followed by genre titles

    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
     செயல்படுத்த
    0.56
     organización
    0.52
    読んで
    0.52
    栉
    0.52
     whitespace
    0.50
     दुल्हन
    0.50
     સામ
    0.49
     fortiter
    0.48
    ificación
    0.48
    gewicht
    0.47
    POSITIVE LOGITS
     Pott
    0.54
     feared
    0.53
     made
    0.52
     known
    0.51
     Known
    0.48
     Easily
    0.47
    ід
    0.46
     imposed
    0.46
     e
    0.46
     ceded
    0.46
    Activations Density 0.000%

    No Known Activations