© 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. 28509
    Prev
    Next
    INDEX
    Explanations

    questions and numerical sequences

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

    The neuron is looking for numeric tokens (digits or multi‐digit numbers) in the document.

    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
     all
    -0.88
     such
    -0.85
     lú
    -0.80
     الظ
    -0.80
     apparently
    -0.78
     trying
    -0.77
     graciosas
    -0.77
     cannot
    -0.76
     Zusch
    -0.75
     three
    -0.73
    POSITIVE LOGITS
    ilización
    1.04
    hecimento
    0.96
     nachdem
    0.94
     organisme
    0.91
    AntiForgery
    0.90
    ERG
    0.90
    ötet
    0.90
    Κ
    0.88
    rescence
    0.88
    ICIAS
    0.88
    Activations Density 0.002%

    No Known Activations