© 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. 166583
    Prev
    Next
    INDEX
    Explanations

    fake Rolex

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

    eager for education

    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
     chari
    0.50
     cannons
    0.47
    ixin
    0.46
     ξεκ
    0.46
     км
    0.46
    nial
    0.46
    opilot
    0.45
     ܠ
    0.45
     глоба
    0.45
     дви
    0.45
    POSITIVE LOGITS
    kap
    0.57
    ويه
    0.52
    student
    0.49
    特别是
    0.49
     Norfolk
    0.47
    చిన
    0.46
    وض
    0.45
    פת
    0.45
    簡単な
    0.45
    Cleveland
    0.44
    Activations Density 0.000%

    No Known Activations