© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 1501
    Prev
    Next
    INDEX
    Explanations

    jour JOUR JOURneys

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

    The neuron activates on numeric tokens and figures, detecting quantities and numbers (including decimal values).

    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
    IUrlHelper
    -1.55
     esclusivamente
    -1.47
     множество
    -1.41
     leggermente
    -1.41
    ضی
    -1.39
     forsaken
    -1.38
    ⅜
    -1.37
    .}(
    -1.34
    プライズ
    -1.34
     republicans
    -1.33
    POSITIVE LOGITS
    iling
    1.38
     of
    1.38
    ほら
    1.38
     perguntou
    1.36
    mẫu
    1.35
    过来了
    1.34
     slipped
    1.34
    bonsoir
    1.33
     encantador
    1.33
     respondeu
    1.33
    Activations Density 0.037%

    No Known Activations