© 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. 236955
    Prev
    Next
    INDEX
    Explanations

    seeking needs is basket

    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
    दित
    0.50
    ח
    0.44
    ورو
    0.43
    ط
    0.42
     reel
    0.42
    <0xAE>
    0.41
    収
    0.41
    (“
    0.41
     seniors
    0.40
    CHICAGO
    0.39
    POSITIVE LOGITS
     antena
    0.48
     малень
    0.45
     Toshiba
    0.42
    荿
    0.42
     straightened
    0.42
     Kernel
    0.41
     Quaternion
    0.41
     pensamento
    0.40
     máte
    0.40
     Ds
    0.40
    Activations Density 0.000%

    No Known Activations