© 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. 48023
    Prev
    Next
    INDEX
    Explanations

    cities, battles, languages, or specific items

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

    This neuron fires on programming‐style tokens—especially uppercase identifiers, underscores, and hex or code constants.

    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
    selben
    -1.59
    anadas
    -1.55
    KommentareTeilen
    -1.52
     专业
    -1.45
    éter
    -1.44
    珵
    -1.43
    糌
    -1.40
     เรา
    -1.39
     ſol
    -1.38
     汽车
    -1.37
    POSITIVE LOGITS
    (
    1.77
     not
    1.48
     it
    1.43
     importante
    1.41
    D
    1.41
    _
    1.32
    S
    1.30
     (
    1.30
    E
    1.30
    =
    1.29
    Activations Density 0.004%

    No Known Activations