© 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. 176904
    Prev
    Next
    INDEX
    Explanations

    exhibition stand contractors

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

    disparity, issues, thinking

    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
     Treats
    0.52
     devotes
    0.50
     Treating
    0.49
     Prepare
    0.47
     OFFSET
    0.47
     Heel
    0.46
     壁
    0.46
    <unused1112>
    0.46
     pdelay
    0.45
     Subtract
    0.45
    POSITIVE LOGITS
    ﺎ
    0.52
    \
    0.50
    task
    0.47
    да
    0.46
    inta
    0.46
    ي
    0.46
    study
    0.46
    ح
    0.45
    edit
    0.45
    z
    0.45
    Activations Density 1.484%

    No Known Activations