© 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. 65795
    Prev
    Next
    INDEX
    Explanations

    executive authority

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

    The neuron is primarily activated by numeric tokens—digits, numbers, and related quantifiers.

    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
    APPLICATIONS
    -0.75
    uckle
    -0.75
    لے
    -0.75
     Modena
    -0.74
    denim
    -0.73
    TICKETS
    -0.73
     Conde
    -0.72
    דה
    -0.72
     Codable
    -0.71
     condenser
    -0.69
    POSITIVE LOGITS
    bru
    0.81
    bf
    0.77
     ochrony
    0.77
    blos
    0.77
     %
    0.72
    ("%
    0.71
    ながら
    0.70
    avadoc
    0.69
     Ά
    0.68
     success
    0.68
    Activations Density 0.019%

    No Known Activations