© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99661
    Prev
    Next
    INDEX
    Explanations

    average of ranks

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

    The neuron activates on numeric tokens (digits or number literals) 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
     hanggang
    -0.75
    merry
    -0.72
    teman
    -0.71
     natin
    -0.71
    olusi
    -0.70
    此事
    -0.67
     pamię
    -0.67
    lamó
    -0.67
     jadi
    -0.66
    楽しみです
    -0.66
    POSITIVE LOGITS
     average
    2.50
    average
    2.36
     midpoint
    2.34
     halfway
    2.14
    Average
    2.11
     averages
    2.05
     averaged
    2.03
    avg
    2.02
     Average
    1.99
    平均
    1.95
    Activations Density 0.018%

    No Known Activations