© 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. 63407
    Prev
    Next
    INDEX
    Explanations

    describing physical measurements

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

    callable, sqrt, dot

    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
    return
    0.46
    watch
    0.46
    ALTER
    0.44
    entukan
    0.44
     ng
    0.43
    การ
    0.43
    js
    0.43
     औपचारिक
    0.43
    i
    0.43
    wards
    0.42
    POSITIVE LOGITS
     zodat
    0.45
     ########.
    0.44
     ሀ
    0.43
     ವೇ
    0.43
    椭
    0.42
     gravité
    0.42
    ﾝ
    0.41
    ूम
    0.41
    ্ধু
    0.40
     gravedad
    0.40
    Activations Density 0.000%

    No Known Activations