© 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. 114193
    Prev
    Next
    INDEX
    Explanations

    scientific citations and data

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

    scientific fields and methods

    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
    paramet
    0.50
    seven
    0.46
    parameter
    0.46
     trajectories
    0.45
     morphological
    0.45
    +}(
    0.44
    était
    0.44
     interventions
    0.43
    strategies
    0.43
     angiogenic
    0.42
    POSITIVE LOGITS
     مشرف
    0.45
    纽约
    0.44
    跎
    0.44
    髡
    0.44
     किराया
    0.43
    惀
    0.43
     megaphone
    0.42
    튜디오
    0.42
    ൊരു
    0.41
    装饰
    0.41
    Activations Density 0.039%

    No Known Activations