© 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. 205119
    Prev
    Next
    INDEX
    Explanations

    freight flow, corporate groups, Higgs boson

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

    initially chosen experience

    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
     Cas
    0.48
     Instinct
    0.47
     Sch
    0.46
     اللا
    0.46
     substitutions
    0.45
    엽
    0.45
    ｝
    0.45
     Austral
    0.44
     Elite
    0.44
     clon
    0.44
    POSITIVE LOGITS
    itorial
    0.46
    odată
    0.44
    ovima
    0.44
     preparada
    0.43
    𝚎
    0.43
    Goal
    0.43
    Mua
    0.43
    ovem
    0.43
    Strategic
    0.43
    uali
    0.43
    Activations Density 0.001%

    No Known Activations