© 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. 103043
    Prev
    Next
    INDEX
    Explanations

    follow any responses

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

    AI algorithms and data processing

    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
    Negative Logits
    ro
    0.59
    res
    0.53
    rentes
    0.53
    razione
    0.50
    membrane
    0.48
    F
    0.48
    should
    0.48
    solved
    0.47
    phosphorylation
    0.47
    isieren
    0.46
    POSITIVE LOGITS
    遇见
    0.48
    颂
    0.47
    当中
    0.46
     karşınız
    0.45
     messageShow
    0.44
     Elemente
    0.44
     authentically
    0.43
    跌
    0.43
    样式
    0.43
    随时
    0.42
    Activations Density 0.001%

    No Known Activations