© 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. 9225
    Prev
    Next
    INDEX
    Explanations

    dictionary/object structures

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

    The neuron triggers on standalone integer literals (numbers) 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
     но
    -2.38
    有著
    -2.28
    ة
    -2.27
    ጧ
    -2.22
    bardier
    -2.16
    thenburg
    -2.14
    蜴
    -2.13
    และ
    -2.11
    NOWLEDG
    -2.05
     plupart
    -2.05
    POSITIVE LOGITS
     There
    3.23
    ve
    2.61
    there
    2.47
    {
    2.42
    of
    2.31
    (
    2.20
     جدید
    2.20
    ?’
    2.17
    km
    2.17
    ig
    2.17
    Activations Density 0.003%

    No Known Activations