© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 127963
    Prev
    Next
    INDEX
    Explanations

    business names and titles

    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
    l
    -2.47
     is
    -2.39
    e
    -2.31
    x
    -2.25
    '
    -2.13
    p
    -1.98
    y
    -1.96
    r
    -1.94
     ...
    -1.94
    in
    -1.77
    POSITIVE LOGITS
    ᐕ
    2.42
     triko
    2.42
    
    2.36
    䛗
    2.34
     Cię
    2.33
    
    2.31
     hijas
    2.28
     jesteśmy
    2.22
    ᷇
    2.22
     cinturón
    2.20
    Activations Density 0.003%

    No Known Activations