© 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. 92288
    Prev
    Next
    INDEX
    Explanations

    laminate cuts

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

    Please don't rely on

    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
     projectors
    0.46
     zone
    0.46
     alumina
    0.46
     perimeter
    0.45
     renderings
    0.44
     anthracite
    0.44
    ↵
    0.43
     REACTORS
    0.41
     irritate
    0.41
     Zone
    0.41
    POSITIVE LOGITS
    方法
    0.54
    Ս
    0.54
    После
    0.52
    imizi
    0.52
    本
    0.52
    水平
    0.52
    缺乏
    0.52
    高
    0.52
    黄
    0.52
    С
    0.51
    Activations Density 0.000%

    No Known Activations