© 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. 9057
    Prev
    Next
    INDEX
    Explanations

    source followed by URL or description

    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
    Not in Any Lists

    No Comments

    Negative Logits
    आगे
    0.51
    텁
    0.49
    stufe
    0.49
     двумя
    0.49
     способность
    0.49
    enhuma
    0.49
     பெண்க
    0.48
    ун
    0.47
     приготов
    0.46
    hasClass
    0.46
    POSITIVE LOGITS
    :
    0.66
     https
    0.60
     from
    0.59
     Sources
    0.57
     Source
    0.56
     från
    0.56
    https
    0.55
    '
    0.53
     Bloomberg
    0.51
    erne
    0.50
    Activations Density 0.003%

    No Known Activations