© 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. 34-GEMMASCOPE-RES-131K
    7. 59774
    Prev
    Next
    INDEX
    Explanations

    horizontal scrolling logic

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

    The neuron is detecting numeric tokens or sequences of digits (i.e., standalone numbers).

    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
     auditory
    -0.81
    landaise
    -0.76
     Архивировано
    -0.75
    heses
    -0.74
    ชื่อ
    -0.74
    roep
    -0.73
    FileChooser
    -0.71
     Photographie
    -0.71
     Threshold
    -0.71
    мм
    -0.71
    POSITIVE LOGITS
     ATTR
    0.91
    深处
    0.81
     layer
    0.81
     geschickt
    0.79
     キャラ
    0.74
     großzü
    0.73
    sweat
    0.72
    waits
    0.72
    Intermediate
    0.71
    的动作
    0.71
    Activations Density 0.004%

    No Known Activations