© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86386
    Prev
    Next
    INDEX
    Explanations

    as shown, reported, indicated

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

    The neuron fires on numerical tokens—ordinals, measurements, figure numbers, or other numeric values 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_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
    儼
    -1.48
    {
    -1.37
    了下
    -1.36
    </i>
    -1.35
    =
    -1.35
    ː
    -1.34
    淪
    -1.32
    ).
    -1.32
    []):
    -1.30
    </h1>
    -1.30
    POSITIVE LOGITS
     of
    2.13
    CAPÍTULO
    1.52
    悫
    1.48
    There
    1.41
    这是一个
    1.30
    佉
    1.30
     there
    1.29
    atangan
    1.28
    
    1.28
    岨
    1.27
    Activations Density 0.020%

    No Known Activations