© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 92256
    Prev
    Next
    INDEX
    Explanations

    speed skater, speed week, speeding

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on occurrences of the word “speed” (in any casing or as part of compounds such as “Speedmaster” or “speeding”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    hearted
    -0.75
     cooper
    -0.74
     cheese
    -0.73
    風が
    -0.73
     advertisement
    -0.71
     foreshadow
    -0.71
    algae
    -0.70
    eru
    -0.69
    raven
    -0.69
     Thermal
    -0.69
    POSITIVE LOGITS
    ier
    1.21
    ometers
    1.07
     gonz
    1.05
     SPEED
    1.00
    sters
    1.00
    way
    0.98
    Speed
    0.97
    ily
    0.96
    boats
    0.95
    ometre
    0.95
    Activations Density 0.017%

    No Known Activations