© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34884
    Prev
    Next
    INDEX
    Explanations

    numbers in mathematical contexts

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

    The neuron strongly activates on the specific number token “14.”

    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
    They
    -2.70
    There
    -2.56
    ・・・・・
    -2.45
    If
    -2.44
    It
    -2.41
     sebelum
    -2.27
    You
    -2.16
    Some
    -2.09
    今朝
    -2.03
     untuk
    -2.02
    POSITIVE LOGITS
    ⧼
    2.30
    鲵
    2.27
    ar
    2.27
    0
    2.17
    led
    2.14
    m
    2.13
    th
    2.13
    c
    2.03
     municipales
    1.98
    ha
    1.92
    Activations Density 0.057%

    No Known Activations