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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109845
    Prev
    Next
    INDEX
    Explanations

    endurance and pushing limits

    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
    odyne
    -1.02
     aventures
    -0.98
    落ち着
    -0.96
     getField
    -0.93
    άνει
    -0.92
    的生活
    -0.91
    ходу
    -0.90
    Jumping
    -0.87
     Barbier
    -0.86
    味は
    -0.85
    POSITIVE LOGITS
     pushing
    1.39
     lactic
    1.38
     endurance
    1.38
     pushes
    1.19
     pushed
    1.18
     anaerobic
    1.14
    FINISH
    1.08
     push
    1.06
     finishing
    1.05
     stamina
    1.04
    Activations Density 0.028%

    No Known Activations