© 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. 2258
    Prev
    Next
    INDEX
    Explanations

    Page, Present, Together

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

    The neuron activates on standalone numeric literals (tokens consisting of digits) in code or 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_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
     Corée
    -0.81
     gunfire
    -0.79
     PRD
    -0.77
    Domen
    -0.76
    insular
    -0.76
    Cambodia
    -0.75
     fasteners
    -0.75
    CHINA
    -0.75
    Charming
    -0.74
    ède
    -0.74
    POSITIVE LOGITS
     Address
    0.88
     Visible
    0.82
    jpg
    0.81
     Detail
    0.80
    atorio
    0.80
    depends
    0.79
     Discuss
    0.79
    ombes
    0.79
     часов
    0.79
    araus
    0.79
    Activations Density 0.003%

    No Known Activations