© 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. 103605
    Prev
    Next
    INDEX
    Explanations

    diagnostics, see, monitor, president, degree

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

    Adriatic Sea, Edinburgh Castle

    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
    ged
    0.54
    ppled
    0.52
    Pct
    0.51
    son
    0.51
    c
    0.51
    m
    0.49
    slow
    0.49
    lau
    0.48
    bani
    0.48
    ses
    0.48
    POSITIVE LOGITS
     scripts
    0.47
     காலம்
    0.45
    ERSHIP
    0.45
     rubric
    0.44
     Scripts
    0.43
    úrese
    0.42
    쿨
    0.41
     xổ
    0.41
     chí
    0.40
    творе
    0.40
    Activations Density 0.001%

    No Known Activations