© 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. 127406
    Prev
    Next
    INDEX
    Explanations

    special characters and code snippets

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

    The neuron selectively activates on numeric tokens (digits, version numbers, percentages, etc.) 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
    ’,
    -1.81
    ”,
    -1.76
    ’
    -1.75
    .
    -1.73
    ,”
    -1.66
    .”
    -1.63
    :
    -1.55
    !”
    -1.49
    емся
    -1.48
     kreatif
    -1.44
    POSITIVE LOGITS
     Selecciona
    1.48
     alrededores
    1.41
    咬牙
    1.40
     hospitales
    1.38
     Seleccione
    1.35
     podido
    1.34
    はこの
    1.34
    нения
    1.33
     '
    1.33
    小心翼翼
    1.32
    Activations Density 0.152%

    No Known Activations