© 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. 59234
    Prev
    Next
    INDEX
    Explanations

    youth sports leagues

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

    The neuron is keyed to spotting alphanumeric codes and numeric tokens—e.g. uppercase identifiers (like “SC” or “U5”) and digit sequences.

    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
     студентов
    -1.00
     学生
    -0.95
    PropTypes
    -0.91
     Students
    -0.84
    Amplitude
    -0.83
    ֵ
    -0.81
    学生
    -0.81
     بسبب
    -0.80
    campus
    -0.80
     Student
    -0.79
    POSITIVE LOGITS
     league
    1.50
     coaches
    1.38
     parents
    1.36
     girls
    1.21
     player
    1.21
    league
    1.19
     age
    1.18
     registration
    1.14
    League
    1.13
    parents
    1.03
    Activations Density 0.024%

    No Known Activations