© 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. 103865
    Prev
    Next
    INDEX
    Explanations

    illness, deriving, center

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

    grief, acidity, plants, heat

    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
    Not in Any Lists

    No Comments

    Negative Logits
    b
    0.46
    res
    0.46
    rep
    0.46
     wading
    0.44
    h
    0.44
    c
    0.44
    mck
    0.44
     nonuniform
    0.44
    similar
    0.43
    e
    0.42
    POSITIVE LOGITS
     ಕೊ
    0.46
    或者是
    0.46
     ለእ
    0.46
    疾病
    0.46
    麼
    0.43
     Guarda
    0.43
    जगी
    0.42
    媚
    0.42
    或是
    0.42
    達
    0.42
    Activations Density 0.001%

    No Known Activations