© 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. 199022
    Prev
    Next
    INDEX
    Explanations

    low fat, low calorie

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

    history and foreign words

    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
     clickable
    0.64
     online
    0.55
     contactless
    0.55
     E
    0.52
     electronically
    0.51
     javascript
    0.50
     velcro
    0.49
     perpendicular
    0.49
     London
    0.49
     electronic
    0.49
    POSITIVE LOGITS
    ศาส
    0.51
     asesin
    0.48
    ímav
    0.46
     نجات
    0.45
    霊
    0.45
    ตำ
    0.44
    ヒト
    0.44
     бого
    0.43
    Gosudarstvennyj
    0.43
    <unused47>
    0.43
    Activations Density 0.001%

    No Known Activations