© 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. 63479
    Prev
    Next
    INDEX
    Explanations

    sports, gardening, and treatments

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

    friendly AI greetings and checks

    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
    取引
    0.48
     ಸಂಗ
    0.48
     عمل
    0.46
    顫
    0.46
    পুত্র
    0.46
    currentState
    0.46
    ந்தார்
    0.46
    quinone
    0.44
    operating
    0.44
    焲
    0.44
    POSITIVE LOGITS
     cert
    0.44
     jas
    0.44
     kan
    0.41
     ab
    0.41
     us
    0.41
    в
    0.40
    ूट
    0.39
     vex
    0.39
     sere
    0.39
     ker
    0.39
    Activations Density 0.000%

    No Known Activations