© 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. 34-GEMMASCOPE-RES-131K
    7. 38511
    Prev
    Next
    INDEX
    Explanations

    HTML xmlns

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

    The neuron is triggered by numeric tokens (sequences of digits), i.e. 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_34/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
     celebration
    -0.74
     célébr
    -0.73
     تشخیص
    -0.71
     Allgemeine
    -0.69
     Edmond
    -0.69
    tula
    -0.68
    ereq
    -0.67
     axial
    -0.66
    zyp
    -0.66
     celebrate
    -0.65
    POSITIVE LOGITS
    そうです
    0.64
     agre
    0.64
    portál
    0.64
    mMap
    0.63
    ั้ง
    0.62
     stove
    0.61
     aces
    0.60
    ǹ
    0.60
     रि
    0.60
     passi
    0.60
    Activations Density 0.074%

    No Known Activations