© 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. 34-GEMMASCOPE-RES-131K
    7. 106831
    Prev
    Next
    INDEX
    Explanations

    menu item numbers, quantities, dates

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

    The main thing this neuron does is find numeric tokens (numbers, dates, measurements, prices, etc.).

    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
     rígida
    -0.85
     tâches
    -0.83
    шев
    -0.74
    GRAFIA
    -0.74
     lacked
    -0.73
     саме
    -0.72
    ių
    -0.72
    PLAUSE
    -0.71
    momile
    -0.71
    ้าว
    -0.71
    POSITIVE LOGITS
    @[
    0.84
    Photography
    0.81
     nörd
    0.80
     Rude
    0.80
    amente
    0.79
     azeite
    0.77
    ಹ
    0.77
    expressions
    0.76
    логические
    0.75
    “[
    0.74
    Activations Density 0.017%

    No Known Activations