© 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. 83099
    Prev
    Next
    INDEX
    Explanations

    Australian broadcasting and science

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

    The neuron activates on numeric tokens, essentially spotting multi‐digit numbers 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_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
    columns
    -0.76
    将
    -0.75
    DG
    -0.73
    constexpr
    -0.71
    ontin
    -0.71
    autoreleasepool
    -0.71
    lug
    -0.70
    del
    -0.69
    resaid
    -0.68
    若
    -0.68
    POSITIVE LOGITS
    líben
    0.90
    ייט
    0.86
     JST
    0.85
    yler
    0.84
    čního
    0.84
    皛
    0.84
     THR
    0.83
    EXTR
    0.82
     tranf
    0.82
     窗
    0.80
    Activations Density 0.017%

    No Known Activations