© 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. 15379
    Prev
    Next
    INDEX
    Explanations

    indicates function or role

    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
     donner
    -1.57
    ⎔
    -1.52
     SOMETHING
    -1.49
    ники
    -1.45
     mancher
    -1.43
     bluza
    -1.42
    ที่มี
    -1.41
     utilizz
    -1.39
     these
    -1.38
    Habe
    -1.38
    POSITIVE LOGITS
     also
    2.48
     to
    1.98
     will
    1.91
    </b>
    1.86
     would
    1.84
     against
    1.73
    </i>
    1.70
     is
    1.64
     cũng
    1.63
     and
    1.61
    Activations Density 0.034%

    No Known Activations