© 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. 106434
    Prev
    Next
    INDEX
    Explanations

    sequel, Resources, copyrighted, groups

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

    data backup services

    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
    😡
    0.45
     countrymen
    0.44
     outweighs
    0.43
     complainants
    0.41
     인한
    0.41
     unreasonable
    0.41
    全市
    0.41
     ಅವರ
    0.40
     miatt
    0.39
     heightened
    0.39
    POSITIVE LOGITS
     Without
    0.52
     revital
    0.52
    溦
    0.50
     utilisée
    0.49
     除了
    0.48
    Stencil
    0.48
     بدون
    0.48
     其实
    0.47
     ব্যবহৃত
    0.47
    迅速
    0.46
    Activations Density 0.001%

    No Known Activations