© 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. 148590
    Prev
    Next
    INDEX
    Explanations

    affiliate business

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

    C: search relevant information

    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
    ье
    0.46
    ской
    0.46
    出力
    0.43
    ндо
    0.43
    ेडकर
    0.41
    系
    0.41
    OS
    0.41
    dal
    0.41
    他
    0.40
    帀
    0.40
    POSITIVE LOGITS
     optomet
    0.56
     GIT
    0.56
     SECOND
    0.52
     điện
    0.51
     CSS
    0.50
     EYE
    0.49
     electrician
    0.49
     AUTO
    0.48
     MIN
    0.48
     Điện
    0.48
    Activations Density 0.000%

    No Known Activations