© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 71461
    Prev
    Next
    INDEX
    Explanations

    Enjoy a savings or a number

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

    explaining why

    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
    Leadership
    0.46
    Files
    0.45
    Relations
    0.45
    Period
    0.44
    Path
    0.44
    記事
    0.44
    ف
    0.44
     Pathfinder
    0.43
    PathTemplate
    0.43
    Contributions
    0.43
    POSITIVE LOGITS
     sweetly
    0.47
    РА
    0.46
    뻑
    0.46
    stoffen
    0.45
    ΡΑ
    0.45
     incre
    0.44
    τα
    0.44
    \},\
    0.44
    kta
    0.44
     inadequ
    0.43
    Activations Density 0.000%

    No Known Activations