© 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. 73697
    Prev
    Next
    INDEX
    Explanations

    United Nation

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

    The neuron selectively activates on numeric tokens—especially standalone numbers, numeric citations/references, figure indices, and code version identifiers.

    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
     além
    -0.81
    ighty
    -0.81
     roule
    -0.79
    ֹת
    -0.78
    andra
    -0.77
     RIC
    -0.74
     réactions
    -0.73
    えている
    -0.73
     annonces
    -0.73
     WALT
    -0.72
    POSITIVE LOGITS
    空中
    0.70
    directories
    0.66
     Selling
    0.65
    句
    0.65
    พระ
    0.63
    海
    0.63
    雨
    0.62
    앙
    0.62
    window
    0.62
     out
    0.62
    Activations Density 0.067%

    No Known Activations