© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22544
    Prev
    Next
    INDEX
    Explanations

    viewport width/height attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    czeniu
    -1.97
     тези
    -1.79
    ୈ
    -1.69
     temática
    -1.65
    معرفی
    -1.64
    ࣭
    -1.61
     มัน
    -1.57
    فایل
    -1.55
    
    -1.52
    ጺ
    -1.52
    POSITIVE LOGITS
    </strong>
    1.91
    徐々に
    1.64
    完全に
    1.63
     the
    1.60
    車を
    1.53
    utilized
    1.51
    どんどん
    1.51
    さまざま
    1.49
    ridescent
    1.49
    沢山
    1.45
    Activations Density 0.002%

    No Known Activations