© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103492
    Prev
    Next
    INDEX
    Explanations

    Genre, IB, Rab, Strict, Caring, Find

    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
    ↵
    -2.69
     trois
    -1.95
    \
    -1.94
     cea
    -1.84
    翃
    -1.84
     we
    -1.83
     succinctly
    -1.80
    要在
    -1.79
     exceedingly
    -1.77
    艄
    -1.77
    POSITIVE LOGITS
     There
    2.23
     These
    2.19
    vantaged
    2.02
     Also
    1.75
     Those
    1.74
     Interestingly
    1.73
     During
    1.73
    CONSIN
    1.70
    獁
    1.59
     plupart
    1.55
    Activations Density 0.213%

    No Known Activations