© 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. 22-GEMMASCOPE-RES-131K
    7. 15836
    Prev
    Next
    INDEX
    Explanations

    scores from sports matches

    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_22/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
     already
    -1.13
     for
    -1.13
    :
    -1.10
     new
    -1.09
     just
    -1.07
     What
    -1.06
     now
    -1.04
    _
    -1.03
     =
    -1.03
     think
    -1.02
    POSITIVE LOGITS
     habido
    1.18
     refugiados
    1.11
    tki
    1.10
     victoire
    1.10
    
    1.09
    Baş
    1.09
    Kode
    1.09
    麃
    1.07
    nements
    1.06
    しくお願い
    1.06
    Activations Density 0.009%

    No Known Activations