© 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. 73836
    Prev
    Next
    INDEX
    Explanations

    spring and fall semesters

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

    The neuron is specialized to detect numeric tokens (i.e. sequences of digits such as dates, phone numbers, counts, or other 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
    glVertex
    -0.75
     huo
    -0.73
    mensa
    -0.72
     padang
    -0.72
    ウェー
    -0.69
     イベント
    -0.69
     kac
    -0.69
     cubo
    -0.69
     ошибки
    -0.68
    模
    -0.68
    POSITIVE LOGITS
     spring
    4.22
     fall
    4.16
     Fall
    4.09
     Spring
    3.89
    Fall
    3.61
     autumn
    3.41
    Spring
    3.33
     Autumn
    3.17
    spring
    3.05
    fall
    2.98
    Activations Density 0.061%

    No Known Activations