© 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-16K
    7. 12163
    Prev
    Next
    INDEX
    Explanations

    house, wall, exterior, interior

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

    security vulnerabilities

    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_16k_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
    하지만
    0.51
    但在
    0.49
    但他
    0.47
    thing
    0.47
    แต่
    0.46
    depth
    0.46
    Z
    0.45
    Доб
    0.44
    Доброго
    0.44
    但
    0.44
    POSITIVE LOGITS
     مولانا
    0.53
     commiss
    0.47
     στον
    0.46
    ți
    0.45
     перево
    0.45
     incrível
    0.45
    rà
    0.44
     στο
    0.44
    сро
    0.44
    ા
    0.44
    Activations Density 0.024%

    No Known Activations