© 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. 102879
    Prev
    Next
    INDEX
    Explanations

    punctuation and foreign characters

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

    dates, calculate, purpose, article, prime

    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
    Negative Logits
     FGFR
    0.46
     पीड़
    0.46
    ী
    0.45
    otoxin
    0.44
    ীম
    0.43
    ताच
    0.43
     eczema
    0.43
    ِّف
    0.42
    يقة
    0.42
    MASS
    0.41
    POSITIVE LOGITS
     discernible
    0.49
    !"
    0.47
    !!"
    0.46
     знамена
    0.46
    핸
    0.46
    ."
    0.45
    emann
    0.45
    lesson
    0.44
    unit
    0.44
     Sebastian
    0.44
    Activations Density 0.001%

    No Known Activations