© 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. 90942
    Prev
    Next
    INDEX
    Explanations

    updates and alerts

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

    spoken sentence

    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
     soybeans
    0.58
    ’).
    0.50
    вания
    0.49
     tendons
    0.49
     sufficient
    0.48
     insufficient
    0.48
     remnants
    0.48
     bureaucrats
    0.48
     tractors
    0.47
    !">
    0.47
    POSITIVE LOGITS
     Wolfram
    0.58
     جيم
    0.52
     ไอ้
    0.51
     മലയാള
    0.50
     Poincaré
    0.49
    Algebra
    0.48
    smile
    0.48
    Smile
    0.48
    page
    0.48
    desde
    0.48
    Activations Density 0.000%

    No Known Activations