© 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. 85163
    Prev
    Next
    INDEX
    Explanations

    ingredients and specifications

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

    advantages or theories

    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
     طور
    0.48
    ;
    0.46
     lưới
    0.46
     повто
    0.45
     выборах
    0.45
     lf
    0.44
     calme
    0.43
     ()
    0.43
     faveur
    0.42
     Reads
    0.42
    POSITIVE LOGITS
    esehatan
    0.50
    Polynomial
    0.47
    聖
    0.46
     मर्यादा
    0.46
    階段
    0.46
    रोला
    0.46
    ыргыз
    0.46
    Setelah
    0.45
     স
    0.45
    巴西
    0.44
    Activations Density 0.003%

    No Known Activations