© 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. 110916
    Prev
    Next
    INDEX
    Explanations

    Kubernetes configurations

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

    The neuron fires on tokens containing numerals (digits) or numeric‐looking strings.

    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
     metric
    -1.43
     metrics
    -1.35
     Metric
    -0.98
    Metric
    -0.93
     Metrics
    -0.91
    metric
    -0.90
    Valores
    -0.77
    ች
    -0.77
     gauge
    -0.76
     measures
    -0.74
    POSITIVE LOGITS
    शा
    0.95
     屋
    0.82
    ayana
    0.81
    EObject
    0.78
    quisa
    0.77
     GameManager
    0.76
    kala
    0.76
    icing
    0.75
    rollable
    0.75
    PackageManager
    0.73
    Activations Density 0.019%

    No Known Activations