© 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. 10-GEMMASCOPE-RES-131K
    7. 118984
    Prev
    Next
    INDEX
    Explanations

    legal citations and numbers

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

    The neuron fires on alphanumeric identifier sequences—strings of digits (and hex letters) such as legal citation numbers or hexadecimal hashes.

    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
     чрезвы
    -1.81
    according
    -1.73
     商务
    -1.57
     孩子
    -1.55
     汽车
    -1.49
     predetermined
    -1.49
     where
    -1.47
     桶
    -1.41
    ;%%
    -1.38
     旅游
    -1.38
    POSITIVE LOGITS
     bienvenue
    1.54
    animity
    1.42
    bolistas
    1.41
     также
    1.38
     hvorfor
    1.36
     даже
    1.36
     également
    1.36
     кух
    1.34
    гляд
    1.32
    8
    1.32
    Activations Density 0.056%

    No Known Activations