© 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. 6957
    Prev
    Next
    INDEX
    Explanations

    dates and locations

    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
     when
    -1.59
     during
    -1.32
     הראשון
    -1.31
     verschillen
    -1.30
    ＞＞
    -1.29
     betrek
    -1.29
     verbeter
    -1.27
    ⸜
    -1.27
    Zitat
    -1.27
    」、「
    -1.26
    POSITIVE LOGITS
    榈
    1.51
    xvii
    1.48
     ۷
    1.44
    都不知道
    1.39
     decisiones
    1.37
    走的
    1.36
     ۳۰
    1.36
     ۶
    1.35
    𐄁
    1.34
    afar
    1.34
    Activations Density 0.021%

    No Known Activations