© 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. 81592
    Prev
    Next
    INDEX
    Explanations

    litigations or sliding

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

    information and app usage

    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
    ;
    0.41
     sweeping
    0.41
    :
    0.41
     lineare
    0.41
    ,
    0.40
     monoclonal
    0.39
     blue
    0.39
     Blue
    0.39
     мг
    0.39
     vii
    0.39
    POSITIVE LOGITS
    িয়নের
    0.52
    cooking
    0.49
    説明
    0.46
     छवि
    0.46
    ᱞ
    0.45
     principais
    0.45
    संगिक
    0.45
    चने
    0.45
    কাহিনী
    0.44
    欵
    0.44
    Activations Density 0.000%

    No Known Activations