© 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. 90925
    Prev
    Next
    INDEX
    Explanations

    channel resistance and temperature

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

    The neuron specializes in spotting numeric specification tokens—i.e. measurements, counts, and numerical values in technical text.

    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
     Estimates
    -0.73
    ดี
    -0.71
    راط
    -0.71
     Gloucester
    -0.68
    esticular
    -0.68
     Suggestions
    -0.67
     Española
    -0.65
     расска
    -0.65
     Teixeira
    -0.65
    ئ
    -0.65
    POSITIVE LOGITS
     models
    1.09
     MODEL
    0.89
    Balls
    0.87
     saturation
    0.85
     modelos
    0.81
     model
    0.81
    model
    0.79
    modelle
    0.79
     choisir
    0.79
     модели
    0.77
    Activations Density 0.009%

    No Known Activations