© 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. 85421
    Prev
    Next
    INDEX
    Explanations

    sports teams and athletes

    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
    ,
    -1.32
     and
    -1.20
    ทั้ง
    -1.18
     =
    -1.17
     furono
    -1.12
     endeavor
    -1.12
     kèm
    -1.11
     endeavour
    -1.10
     Its
    -1.09
     Considerations
    -1.09
    POSITIVE LOGITS
     orina
    1.30
    .’
    1.23
     nomine
    1.20
    QUIS
    1.19
     corsa
    1.19
     Vgl
    1.18
     crisi
    1.17
     ricc
    1.17
     recenti
    1.16
    tences
    1.14
    Activations Density 0.061%

    No Known Activations