© 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. 150026
    Prev
    Next
    INDEX
    Explanations

    carefully researching

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

    introductions and explanations

    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
    odin
    0.51
    of
    0.51
    ET
    0.51
    ov
    0.50
    de
    0.50
     ശ്രമ
    0.50
    mış
    0.49
    templates
    0.49
    din
    0.49
    s
    0.49
    POSITIVE LOGITS
     ammonium
    0.50
    хову
    0.49
     borderColor
    0.49
    ）
    0.48
     ammon
    0.47
     Ма
    0.46
     invertebrate
    0.46
     multim
    0.46
     biking
    0.45
    льбе
    0.45
    Activations Density 0.001%

    No Known Activations