© 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. 34-GEMMASCOPE-RES-131K
    7. 99914
    Prev
    Next
    INDEX
    Explanations

    space launch vehicle

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

    This neuron activates on numeric tokens (any 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
    小說
    -0.85
     Moos
    -0.77
    ULD
    -0.77
    PARATUS
    -0.77
     braço
    -0.73
     contagios
    -0.73
    pann
    -0.73
     regno
    -0.71
     presentaciones
    -0.71
     موثر
    -0.71
    POSITIVE LOGITS
     human
    0.90
     LEO
    0.83
    ֵל
    0.79
     capability
    0.79
     return
    0.79
    mitives
    0.79
     Brom
    0.77
    曜日
    0.77
    ствовать
    0.77
     cre
    0.77
    Activations Density 0.023%

    No Known Activations