© 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. 10-GEMMASCOPE-RES-131K
    7. 105705
    Prev
    Next
    INDEX
    Explanations

    list and descriptive terms

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

    The neuron predominantly responds to numeric tokens and measurements (e.g. integers or decimals) 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_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
     though
    -1.46
    baine
    -1.45
    inafter
    -1.43
    ’
    -1.41
    esthesia
    -1.39
    vae
    -1.36
    uvw
    -1.34
    vaders
    -1.33
     vatten
    -1.33
    zyć
    -1.33
    POSITIVE LOGITS
     jednej
    1.58
     Popis
    1.50
    aktifkan
    1.48
    敺
    1.48
     簡
    1.48
     angene
    1.41
     auténtico
    1.41
     typy
    1.41
     اهمیت
    1.41
     Mereka
    1.41
    Activations Density 0.382%

    No Known Activations