© 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. 238680
    Prev
    Next
    INDEX
    Explanations

    focus, packing, enterprises, upgrade

    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
    Field
    0.46
    ！！！！
    0.45
    Range
    0.44
    AN
    0.43
     >
    0.43
    Diffusion
    0.43
    '
    0.43
     pertinentes
    0.43
     ？
    0.43
    าร
    0.42
    POSITIVE LOGITS
    ikas
    0.46
    mik
    0.46
     නොව
    0.46
    ück
    0.46
    okes
    0.44
     Са
    0.44
    キット
    0.43
    ските
    0.43
     సినీ
    0.43
    über
    0.43
    Activations Density 0.000%

    No Known Activations