© 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. 1740
    Prev
    Next
    INDEX
    Explanations

    numbers followed by periods

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

    The neuron fires on standalone or dotted numeric labels—e.g. section, exercise, theorem, or list numbers.

    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
     ótima
    -1.48
     lojas
    -1.45
     almohada
    -1.31
    蟜
    -1.30
     neighboring
    -1.29
     créée
    -1.27
     Перейти
    -1.27
     esforço
    -1.26
     conteúdo
    -1.26
     varies
    -1.26
    POSITIVE LOGITS
    u
    1.60
    begin
    1.33
     are
    1.33
    U
    1.29
     Gefühle
    1.27
    viä
    1.23
    ere
    1.19
     on
    1.19
    ??
    1.19
    ???
    1.17
    Activations Density 0.071%

    No Known Activations