© 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. 43250
    Prev
    Next
    INDEX
    Explanations

    discussing appearance or style

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

    describing appearance or quality

    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
    대에
    0.47
    ículos
    0.46
    вается
    0.45
     அவர
    0.44
    나라
    0.43
     עם
    0.43
    खोरी
    0.43
    觴
    0.43
    贰章
    0.42
    销量
    0.41
    POSITIVE LOGITS
    。
    0.57
     .
    0.50
    .
    0.50
    ។
    0.49
     while
    0.46
    ".
    0.46
     ime
    0.45
    '.
    0.44
     whilst
    0.43
    .”
    0.43
    Activations Density 0.001%

    No Known Activations