© 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. 67907
    Prev
    Next
    INDEX
    Explanations

    future outlooks

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

    explaining medical and computational functions

    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
     পোষ
    0.46
     হচ্ছেন
    0.46
     Lice
    0.44
    衫
    0.43
     exclusivamente
    0.43
    పోయే
    0.43
    托
    0.43
     applying
    0.42
     ওয়ার
    0.42
     జీవిత
    0.42
    POSITIVE LOGITS
    pdfs
    0.58
    d
    0.52
    fum
    0.52
    s
    0.49
    utum
    0.48
    in
    0.47
    สดง
    0.46
     تاثیر
    0.46
    emor
    0.46
    f
    0.45
    Activations Density 0.000%

    No Known Activations