© 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. 173844
    Prev
    Next
    INDEX
    Explanations

    fishing bait and oval mirrors

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

    suggest it's

    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
    c
    0.59
    assing
    0.58
    <start_of_image>
    0.54
    ypes
    0.46
    n
    0.46
    ying
    0.46
    ON
    0.45
    This
    0.44
    OF
    0.44
    HR
    0.44
    POSITIVE LOGITS
    формация
    0.57
     忄
    0.54
     контроля
    0.54
     prestación
    0.54
     forem
    0.54
     рынке
    0.53
     enfermos
    0.51
     Laufe
    0.50
     trži
    0.50
     Verlust
    0.49
    Activations Density 0.000%

    No Known Activations