© 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. 108767
    Prev
    Next
    INDEX
    Explanations

    non-starters

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

    common nouns and descriptive 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
    诺
    0.49
     pager
    0.47
    денциа
    0.46
    ющих
    0.45
     Geiger
    0.43
    能够
    0.43
     plupart
    0.43
     predictable
    0.43
    корд
    0.43
    징
    0.43
    POSITIVE LOGITS
     বৎ
    0.48
     했는데
    0.48
     Moisture
    0.47
     Dokument
    0.44
     แล้ว
    0.44
    dsb
    0.44
    law
    0.42
     voluto
    0.41
     **,
    0.41
    stoffe
    0.40
    Activations Density 0.000%

    No Known Activations