© 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. 85541
    Prev
    Next
    INDEX
    Explanations

    batting average, winning percentage

    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
     alleged
    -1.44
     a
    -1.41
     escuelas
    -1.39
     events
    -1.38
    𝟔
    -1.33
     歳
    -1.31
     sicht
    -1.30
     gelieb
    -1.28
     Erinnerungen
    -1.26
    荟
    -1.26
    POSITIVE LOGITS
     if
    1.51
     öf
    1.42
     campion
    1.41
     teu
    1.41
     Sofía
    1.38
    佧
    1.38
     hej
    1.34
     aparat
    1.30
     Cagliari
    1.29
     Kalifor
    1.29
    Activations Density 0.007%

    No Known Activations