© 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. 135101
    Prev
    Next
    INDEX
    Explanations

    sports, great, beginning, love, working

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

    objective without blocking

    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
     वै
    0.52
     ቀ
    0.52
     ಬದಲ
    0.51
     चोट
    0.48
     지방
    0.47
     bảng
    0.47
     작성
    0.46
     상수
    0.46
     dây
    0.45
     쌍
    0.45
    POSITIVE LOGITS
    ਕ
    0.54
    src
    0.54
    EN
    0.47
    posit
    0.46
    sour
    0.46
    cli
    0.46
    تهم
    0.45
    l
    0.45
    Heather
    0.44
    lich
    0.44
    Activations Density 0.000%

    No Known Activations