© 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. 92219
    Prev
    Next
    INDEX
    Explanations

    pure and natural

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

    blush rises

    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
    .
    0.50
    powerful
    0.49
    nano
    0.49
    icro
    0.48
    national
    0.48
     jeff
    0.48
    ag
    0.47
    antic
    0.47
    ارق
    0.46
    end
    0.46
    POSITIVE LOGITS
    较高的
    0.50
     λα
    0.48
     خرید
    0.46
     Puja
    0.46
    务
    0.46
     அள
    0.45
     DISPLAYS
    0.45
     सवारी
    0.45
    书
    0.45
     विद्या
    0.44
    Activations Density 0.002%

    No Known Activations