© 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. 113140
    Prev
    Next
    INDEX
    Explanations

    There have been followed by quantity

    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
     currently
    -2.16
    es
    -1.78
     most
    -1.67
     various
    -1.66
    未必
    -1.60
     both
    -1.59
     AND
    -1.57
     Fähigkeit
    -1.56
     are
    -1.55
     usually
    -1.55
    POSITIVE LOGITS
     able
    1.63
    hilangan
    1.63
     通过
    1.55
    έα
    1.47
     uſe
    1.44
    ෆ
    1.44
    ंत्री
    1.42
     száz
    1.42
    Entonces
    1.41
    ۸
    1.39
    Activations Density 0.045%

    No Known Activations