© 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. 10-GEMMASCOPE-RES-131K
    7. 60314
    Prev
    Next
    INDEX
    Explanations

    display math

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

    The neuron activates on standalone numeric tokens (integers or decimals) in the 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_10/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
     was
    -1.85
     neumáticos
    -1.70
     and
    -1.68
     creada
    -1.60
     —
    -1.59
     cómics
    -1.57
    など
    -1.48
     hermosos
    -1.45
     bocetos
    -1.42
     presentada
    -1.41
    POSITIVE LOGITS
     any
    1.63
    笮
    1.55
     Their
    1.55
     gratuites
    1.52
    عادة
    1.46
     Actually
    1.45
     légales
    1.45
     ordinaires
    1.44
     henceforth
    1.41
    俢
    1.41
    Activations Density 0.012%

    No Known Activations