© 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. 40951
    Prev
    Next
    INDEX
    Explanations

    cornerstone of fat

    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
     invigor
    0.52
     invigorating
    0.52
     exuber
    0.49
    slideDuplicate
    0.48
     uridine
    0.47
     स्थानांतरित
    0.46
     Emiliano
    0.46
    <unused556>
    0.45
     ido
    0.45
     plabic
    0.45
    POSITIVE LOGITS
    GT
    0.49
    API
    0.48
    2
    0.47
    TO
    0.45
    ө
    0.45
    ↵↵
    0.44
    orta
    0.43
    irst
    0.42
    CT
    0.42
    action
    0.42
    Activations Density 0.001%

    No Known Activations