© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26415
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

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

    The neuron is selectively activating on numeric tokens (i.e. standalone numbers, measurements, or other digit sequences).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    スコット
    -0.78
    arbeid
    -0.74
    問合せ
    -0.73
     аналоги
    -0.72
     greatest
    -0.71
     đoán
    -0.71
     ajuda
    -0.71
     here
    -0.71
    ||}
    -0.70
    Fü
    -0.70
    POSITIVE LOGITS
     anzub
    0.78
    ค้า
    0.77
    ANTES
    0.74
    лети
    0.73
     cheque
    0.72
    ϱ
    0.71
    ̘
    0.71
    flü
    0.71
    nī
    0.70
     Publ
    0.69
    Activations Density 0.035%

    No Known Activations