© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 6954
    Prev
    Next
    INDEX
    Explanations

    college football playoff

    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_34/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
     retracted
    -0.83
    关卡
    -0.82
     basket
    -0.73
     Franti
    -0.72
     Berg
    -0.70
     accept
    -0.70
     Gilli
    -0.70
    締切
    -0.69
     Moy
    -0.68
    鏟
    -0.68
    POSITIVE LOGITS
     Alabama
    1.23
    Alabama
    1.19
     playoff
    1.16
     CFP
    1.07
     Ohio
    1.05
    Oklahoma
    0.97
     Oklahoma
    0.97
    Ohio
    0.93
     Clemson
    0.91
    College
    0.87
    Activations Density 0.020%

    No Known Activations