© 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. 10-GEMMASCOPE-RES-131K
    7. 41105
    Prev
    Next
    INDEX
    Explanations

    date/time formats

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

    The neuron detects scientific alphanumeric identifiers and names—especially gene/protein symbols, plasmid codes, and Latin species names.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    荭
    -1.98
    肫
    -1.73
     совершенно
    -1.65
    
    -1.65
    𞤤
    -1.61
    袛
    -1.60
    鲎
    -1.60
    看着他
    -1.56
     hroz
    -1.55
    薆
    -1.55
    POSITIVE LOGITS
    ↵
    2.16
    ка
    1.59
    ſelf
    1.56
     на
    1.55
    ⭐
    1.55
     в
    1.52
    ку
    1.49
    公子
    1.48
     как
    1.47
     Пет
    1.46
    Activations Density 0.003%

    No Known Activations