© 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. 22-GEMMASCOPE-RES-131K
    7. 98492
    Prev
    Next
    INDEX
    Explanations

    Seal, Holland, Islanders, forms, tr

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

    The neuron strongly activates on numeric tokens (e.g. integers or decimals), i.e. it detects 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_22/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
    new
    -1.51
    "
    -1.48
     nuevas
    -1.43
    ...
    -1.38
    !
    -1.38
     new
    -1.38
     neuen
    -1.33
    &
    -1.32
     T
    -1.28
     nuevos
    -1.22
    POSITIVE LOGITS
     TÉ
    1.52
     parachoque
    1.45
     rése
    1.45
    ⑊
    1.44
    yczna
    1.43
    produksi
    1.42
    rably
    1.42
    pography
    1.41
    灵气
    1.38
    ributes
    1.38
    Activations Density 0.114%

    No Known Activations