© 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. 10-GEMMASCOPE-RES-131K
    7. 128504
    Prev
    Next
    INDEX
    Explanations

    French conjunction "et"

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

    The neuron fires on standalone numeric tokens (numbers, including integers and decimals).

    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
    a
    -3.06
    नलोड
    -2.89
    able
    -2.89
    我先
    -2.81
    quelize
    -2.78
    Ꮸ
    -2.56
    最后由
    -2.44
    ade
    -2.44
    鸶
    -2.44
     They
    -2.41
    POSITIVE LOGITS
     pretende
    3.05
    anglais
    2.63
     saluti
    2.50
     แต่
    2.47
    何回
    2.36
    緇
    2.30
     comunica
    2.30
    Skocz
    2.28
     eccellente
    2.27
     leggi
    2.23
    Activations Density 0.001%

    No Known Activations