© 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. 56703
    Prev
    Next
    INDEX
    Explanations

    Martin sparked minds legs

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

    communication styles & differences

    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
     лига
    0.52
    <thead>
    0.49
     Syllabus
    0.48
     Cagliari
    0.47
    ۰
    0.47
    riteria
    0.46
     आश्चर्य
    0.46
    '">
    0.46
     리그
    0.45
     മതി
    0.45
    POSITIVE LOGITS
     trying
    0.47
     chewed
    0.47
     temporally
    0.46
    og
    0.46
    ijer
    0.45
    _
    0.45
     it
    0.45
     awhile
    0.45
     gebruik
    0.44
     temporarily
    0.44
    Activations Density 0.000%

    No Known Activations