© 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. 59839
    Prev
    Next
    INDEX
    Explanations

    football yards and touchdowns

    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
     fichiers
    -0.81
     módulos
    -0.77
     diagnóstico
    -0.74
    vented
    -0.74
     poč
    -0.72
     groot
    -0.71
     проектов
    -0.71
     mediodía
    -0.71
    シピ
    -0.70
    lynn
    -0.70
    POSITIVE LOGITS
     runs
    1.30
     sneak
    1.19
     run
    1.15
     plunged
    1.12
     plung
    1.09
     plunge
    1.06
     sne
    1.04
    run
    1.04
    Run
    0.97
     running
    0.96
    Activations Density 0.007%

    No Known Activations