© 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. 75589
    Prev
    Next
    INDEX
    Explanations

    voltage after input

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

    specific nouns and concepts

    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
    完整
    0.43
     võimalik
    0.43
    IAN
    0.42
     సంబంధ
    0.41
    ENTIAL
    0.40
     exemplaire
    0.40
     purposes
    0.39
     genotype
    0.39
    滴
    0.39
     epitope
    0.39
    POSITIVE LOGITS
    ុ
    0.52
     marít
    0.46
     traw
    0.46
     Buckeyes
    0.45
     Verd
    0.44
     чёр
    0.44
     व्याप
    0.44
    ຯ
    0.44
     Manufact
    0.44
     Gracias
    0.42
    Activations Density 0.001%

    No Known Activations