© 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. 67998
    Prev
    Next
    INDEX
    Explanations

    asp.net mvc

    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
     tuer
    -2.19
    .
    -2.09
    龗
    -2.09
    敺
    -1.99
    韡
    -1.98
     éx
    -1.94
     mâle
    -1.88
     delantero
    -1.88
    獁
    -1.86
     louer
    -1.84
    POSITIVE LOGITS
     and
    2.78
    ;;)
    2.23
     is
    2.22
     versus
    2.06
     in
    2.03
    alakip
    2.02
     be
    2.02
     to
    1.88
     or
    1.86
     by
    1.78
    Activations Density 0.016%

    No Known Activations