© 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. 22-GEMMASCOPE-RES-131K
    7. 39800
    Prev
    Next
    INDEX
    Explanations

    mathematical and technical terms

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

    The neuron activates on numeric tokens (dates, measurements, counts, decimals, etc.), i.e. it detects numbers 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_22/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
     PET
    -0.81
    ㅁ
    -0.77
    ой
    -0.74
    SSH
    -0.73
     PO
    -0.73
    forKey
    -0.71
    Compassion
    -0.71
    Ayo
    -0.70
     PEN
    -0.70
    ","","
    -0.69
    POSITIVE LOGITS
    vud
    0.91
     régal
    0.88
     ждет
    0.85
     conecta
    0.84
    quante
    0.83
    ittin
    0.83
     هوش
    0.80
     cirugía
    0.77
     Thành
    0.76
     busiest
    0.75
    Activations Density 0.074%

    No Known Activations