© 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. 46044
    Prev
    Next
    INDEX
    Explanations

    optimized HTTP

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

    OpenAI started

    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
    HELP
    0.46
    Help
    0.44
    سك
    0.44
     sten
    0.44
    দম
    0.43
     Benedict
    0.42
    ל
    0.42
    ,
    0.42
     HELP
    0.41
     Beno
    0.41
    POSITIVE LOGITS
    ysets
    0.56
    ensión
    0.53
    の時間
    0.52
    əs
    0.51
    のことを
    0.50
     ನಡೆ
    0.48
    estar
    0.48
    yness
    0.48
    owntown
    0.47
    ertime
    0.47
    Activations Density 0.001%

    No Known Activations