© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 80714
    Prev
    Next
    INDEX
    Explanations

    about a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     использова
    0.62
     utilizzato
    0.53
    囩
    0.52
     маршру
    0.51
     spacetime
    0.50
     utilizzati
    0.50
     allyl
    0.49
    $',
    0.49
     Schwarzschild
    0.47
     utilised
    0.47
    POSITIVE LOGITS
    1
    0.55
    im
    0.52
    5
    0.48
    undo
    0.48
    Son
    0.48
    R
    0.47
    Aurora
    0.47
    und
    0.46
    Liquid
    0.46
    Drop
    0.44
    Activations Density 0.001%

    No Known Activations