© 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. 108441
    Prev
    Next
    INDEX
    Explanations

    young athletes and players

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

    The neuron is highly sensitive to numeric tokens (e.g. years, ages, scores, and other statistics).

    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
     veteran
    -1.53
    Veteran
    -1.39
     Veteran
    -1.29
     veterans
    -1.08
     Veterans
    -0.95
    veter
    -0.95
     experienced
    -0.89
    Veterans
    -0.84
     veter
    -0.82
    Experienced
    -0.80
    POSITIVE LOGITS
    atosis
    0.86
     sensation
    0.85
    нень
    0.82
    Nazi
    0.78
    QWidget
    0.76
     coco
    0.76
     phen
    0.76
    ⭐️
    0.73
    اصر
    0.72
    Desc
    0.71
    Activations Density 0.026%

    No Known Activations