© 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. 22-GEMMASCOPE-RES-131K
    7. 93432
    Prev
    Next
    INDEX
    Explanations

    connecting clauses

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

    The neuron activates on numeric tokens, i.e. multi‐digit numbers (including integers and decimals) in the 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_22/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
     ль
    -0.92
    ハウ
    -0.85
    的基本
    -0.85
    开头
    -0.82
    ABETH
    -0.82
    ("-");
    -0.78
    corrência
    -0.78
    meti
    -0.78
    去了
    -0.77
    decre
    -0.75
    POSITIVE LOGITS
     his
    0.90
     llamaba
    0.81
    ૩
    0.77
    hydrogenase
    0.77
    TypeEnum
    0.76
    FormatException
    0.75
     犬
    0.75
     their
    0.75
    فس
    0.74
    étant
    0.74
    Activations Density 0.075%

    No Known Activations