© 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. 72013
    Prev
    Next
    INDEX
    Explanations

    years and months

    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
     povezave
    -1.61
    了许多
    -1.54
    lepaskan
    -1.48
    了很多
    -1.45
    /
    -1.41
    two
    -1.41
     われ
    -1.36
     is
    -1.36
    .*")]
    -1.34
    www
    -1.31
    POSITIVE LOGITS
     ultimi
    1.54
    balanceOf
    1.52
    
    1.47
    dịch
    1.44
     綺麗
    1.43
     of
    1.39
    importante
    1.38
    翆
    1.38
     aſſ
    1.34
    calidad
    1.34
    Activations Density 0.135%

    No Known Activations