© 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. 167974
    Prev
    Next
    INDEX
    Explanations

    import statements

    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
    它的
    0.44
     生成
    0.42
     横
    0.41
     workload
    0.40
     初始化
    0.40
     ActionResult
    0.40
     Initiate
    0.40
     getBitmap
    0.38
     DAT
    0.38
    萤
    0.38
    POSITIVE LOGITS
    hado
    0.46
    all
    0.44
    جميع
    0.44
    Trump
    0.43
    Putin
    0.42
    lyrics
    0.42
    Cabe
    0.42
    remarkable
    0.41
    don
    0.40
    lip
    0.40
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.