© 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. 58307
    Prev
    Next
    INDEX
    Explanations

    contrasting with others

    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
     prostřed
    -1.29
    
    -1.17
    CTest
    -1.17
     礼物
    -1.15
     rám
    -1.13
     dovrebbero
    -1.12
     reparación
    -1.11
     empleos
    -1.09
     سبورت
    -1.08
     nettsted
    -1.06
    POSITIVE LOGITS
    我喜欢
    1.44
     otros
    1.31
    It
    1.31
    After
    1.28
     for
    1.26
    Other
    1.26
    There
    1.23
                   
    1.22
                 
    1.21
     to
    1.20
    Activations Density 0.035%

    No Known Activations