© 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. 217977
    Prev
    Next
    INDEX
    Explanations

    companies contractors, buffet table, workers, animals Cattle

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

    workflow, workflow

    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
    जो
    0.66
    कोई
    0.54
    น
    0.52
    ン
    0.50
    इन
    0.48
     regiones
    0.48
    １
    0.48
    љ
    0.47
    ج
    0.47
    उच्च
    0.47
    POSITIVE LOGITS
    wurf
    0.54
    blichen
    0.52
    HOB
    0.50
     wollten
    0.49
    ZEN
    0.49
    ip
    0.48
    furt
    0.48
    wahl
    0.48
    wender
    0.47
    Workflow
    0.47
    Activations Density 0.000%

    No Known Activations