© 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. 41252
    Prev
    Next
    INDEX
    Explanations

    following the

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

    extract, reformat, prepare

    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
     IDA
    0.46
    に
    0.46
     uses
    0.45
    На
    0.45
    。
    0.45
     IT
    0.45
    魘
    0.45
     I
    0.44
     [+
    0.43
     {{
    0.43
    POSITIVE LOGITS
    ká
    0.51
    aucune
    0.49
    lend
    0.48
    mouseout
    0.47
     लड़
    0.46
    packets
    0.46
    бычно
    0.46
     ହ
    0.45
     భారతదేశ
    0.45
     හ
    0.45
    Activations Density 0.000%

    No Known Activations