© 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. 6891
    Prev
    Next
    INDEX
    Explanations

    sign or signs

    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
    Negative Logits
    </h2>
    -1.83
    萊
    -1.49
    اگر
    -1.45
    而
    -1.45
    ↵
    -1.31
    WATER
    -1.30
     utterly
    -1.30
     .
    -1.30
    توضیحات
    -1.30
    Although
    -1.29
    POSITIVE LOGITS
     signs
    1.96
    沩
    1.82
    疍
    1.73
    鲧
    1.67
    總是
    1.66
     ſy
    1.64
    ECTOS
    1.60
    廰
    1.59
    
    1.59
    勦
    1.59
    Activations Density 0.020%

    No Known Activations