© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48834
    Prev
    Next
    INDEX
    Explanations

    effort and movement

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

    The neuron fires strongly on exhortative sports commentary—imperative, motivational phrases (especially “run faster”–type calls to action).

    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
    Serialize
    -0.81
    znej
    -0.78
     Aquatic
    -0.75
     Serialize
    -0.75
    bier
    -0.75
    ₖ
    -0.73
    uxxxx
    -0.73
     Slo
    -0.71
     Steer
    -0.71
     Kaz
    -0.69
    POSITIVE LOGITS
     runs
    1.38
     running
    1.14
    Runs
    1.13
     movement
    1.00
     pressing
    0.97
    跑
    0.97
     tracking
    0.96
     run
    0.93
     work
    0.91
    Running
    0.91
    Activations Density 0.009%

    No Known Activations