© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 65250
    Prev
    Next
    INDEX
    Explanations

    native speaker, along with, listed, nearest, behind

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

    The neuron activates on numeric content—quantities, dates, counts, and related terms (e.g. anniversaries, measurements, and rounding instructions).

    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
     these
    -1.88
     each
    -1.75
     only
    -1.73
    These
    -1.72
     and
    -1.72
     both
    -1.68
     all
    -1.65
     всегда
    -1.61
     one
    -1.61
     with
    -1.61
    POSITIVE LOGITS
     tien
    1.84
     recente
    1.81
     dezelve
    1.78
     uſ
    1.78
     italia
    1.75
    
    1.66
     zoude
    1.66
     ín
    1.63
    了些
    1.60
    
    1.60
    Activations Density 0.134%

    No Known Activations