© 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. 97962
    Prev
    Next
    INDEX
    Explanations

    computer vision researchers

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

    The neuron strongly activates on multi‐digit numeric tokens (e.g. years, reference numbers, counts).

    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
    かた
    -0.81
    mē
    -0.73
    >-
    -0.71
     flapping
    -0.71
    พอ
    -0.71
    台北
    -0.71
    Unmount
    -0.70
    WEST
    -0.70
    FileSize
    -0.69
    Открыть
    -0.68
    POSITIVE LOGITS
     image
    1.54
     Image
    1.29
     OpenCV
    1.24
    image
    1.21
     images
    1.14
     pixel
    1.14
     Vision
    1.13
     pixels
    1.12
    opencv
    1.12
     scene
    1.08
    Activations Density 0.029%

    No Known Activations