© 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. 22-GEMMASCOPE-RES-131K
    4. 68456
    Prev
    Next
    INDEX
    Explanations

    mathematical and programming syntax

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

    The neuron is responsive to tokens containing uppercase letters or digits.

    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
    oterapia
    -0.85
     backstory
    -0.82
    rosi
    -0.81
    белый
    -0.79
     mercantile
    -0.79
    妡
    -0.79
     توسط
    -0.78
    gelijke
    -0.77
     Zad
    -0.77
     menstru
    -0.77
    POSITIVE LOGITS
     stesso
    0.88
    纜
    0.84
     aquele
    0.79
     bác
    0.77
    ”?
    0.77
    璐
    0.77
     and
    0.76
     khoa
    0.75
     følgende
    0.74
    ようで
    0.73
    Activations Density 0.032%

    No Known Activations