© 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. 2032
    Prev
    Next
    INDEX
    Explanations

    contest plane

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

    The neuron fires on numeric designators—digits, numerical model or channel identifiers, and frequency/unit values—in technical contexts.

    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
    ibration
    -0.74
    jiang
    -0.72
    zeko
    -0.72
    owaniu
    -0.72
     gluco
    -0.71
    нения
    -0.70
     telemetry
    -0.69
     Vortrag
    -0.69
     leveling
    -0.68
     gestern
    -0.68
    POSITIVE LOGITS
     unlimited
    0.82
     Unlimited
    0.81
     Contest
    0.79
     Combat
    0.79
     contest
    0.78
    Unlimited
    0.77
     plane
    0.75
     contests
    0.74
     Prez
    0.73
    Contest
    0.72
    Activations Density 0.013%

    No Known Activations