© 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. 65572
    Prev
    Next
    INDEX
    Explanations

    punctuation and list items

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

    era together or log every

    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
     musically
    0.49
     rekonstru
    0.48
     musicale
    0.47
    v
    0.46
     discours
    0.45
     subm
    0.44
    c
    0.43
    panorama
    0.42
     stylist
    0.42
     monograph
    0.42
    POSITIVE LOGITS
    ysh
    0.52
     ಸ್ಥಳ
    0.49
    ខ្ញុំ
    0.48
     أل
    0.47
     খাওয়া
    0.47
     أجل
    0.47
    ଥି
    0.47
     હતું
    0.46
    ために
    0.46
     *}
    0.46
    Activations Density 0.001%

    No Known Activations