© 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. 16-GEMMASCOPE-2-RES-262K
    7. 138186
    Prev
    Next
    INDEX
    Explanations

    shades and blinds

    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_16_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
     Atual
    0.70
     História
    0.58
     Asamblea
    0.58
    тивов
    0.58
    ק
    0.57
     atual
    0.57
    ですか
    0.57
    τή
    0.56
     dissolve
    0.56
    Storia
    0.56
    POSITIVE LOGITS
    ,
    0.70
    smanship
    0.58
    ছে
    0.57
    aring
    0.56
    ades
    0.56
    ól
    0.53
    agen
    0.52
    arga
    0.52
    ATION
    0.52
    ,​
    0.52
    Activations Density 0.002%

    No Known Activations