© 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. 111061
    Prev
    Next
    INDEX
    Explanations

    conference, industry, titles, insurance

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

    is it

    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
     चर्चित
    0.47
     pledged
    0.44
    閥
    0.44
     MALL
    0.42
     Só
    0.42
     টিম
    0.42
     sack
    0.41
    ೇನೆ
    0.40
     regrets
    0.40
     mí
    0.40
    POSITIVE LOGITS
    ศูนย์
    0.48
     dzieci
    0.45
    อนไลน์
    0.45
    (">
    0.44
    햇
    0.44
     நிலை
    0.44
     اعتق
    0.43
     gebruikers
    0.43
     사용
    0.43
     дети
    0.42
    Activations Density 0.000%

    No Known Activations