© 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. 213346
    Prev
    Next
    INDEX
    Explanations

    Medicare requirements, airport, neglect, debris

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

    operational logs, reduce costs, simple affine

    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
    γι
    0.53
    cales
    0.51
    чал
    0.48
    ಾ
    0.48
    ۇل
    0.47
    hyung
    0.45
    ennials
    0.45
    νοι
    0.45
    кры
    0.44
    ï
    0.44
    POSITIVE LOGITS
     如
    0.51
     Examine
    0.51
     My
    0.49
     世界
    0.49
     సన్ని
    0.49
     Describe
    0.48
     قوات
    0.48
     我的
    0.47
     Compare
    0.46
     Explore
    0.46
    Activations Density 0.000%

    No Known Activations