© 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. 139729
    Prev
    Next
    INDEX
    Explanations

    Expert Certificate

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

    Astronomical Clock, During Precipitation, Torque Multiplication

    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
    У
    0.50
    초
    0.49
    s
    0.48
    원
    0.46
    Y
    0.46
    e
    0.46
    אי
    0.44
    ünk
    0.44
    exports
    0.44
    वाला
    0.44
    POSITIVE LOGITS
     Pred
    0.51
     Vá
    0.49
     Puj
    0.48
     Cable
    0.47
     Cabe
    0.47
     खुशखबरी
    0.47
     एक्सरे
    0.47
     西
    0.46
     ву
    0.46
     Clustering
    0.46
    Activations Density 0.000%

    No Known Activations