© 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. 68858
    Prev
    Next
    INDEX
    Explanations

    completion and creation tasks

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

    file paths, programming, data

    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
    in
    0.63
     frauds
    0.56
    rights
    0.54
     is
    0.52
     does
    0.50
    s
    0.50
     robberies
    0.50
    sf
    0.49
    </strong>
    0.48
    worldwide
    0.48
    POSITIVE LOGITS
    桡
    0.52
    阃
    0.51
    作曲
    0.47
     তাপমাত্রা
    0.46
    胝
    0.45
    刳
    0.44
    鲞
    0.44
     திருதியை
    0.44
    坯
    0.43
     ብ
    0.43
    Activations Density 0.000%

    No Known Activations