© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118627
    Prev
    Next
    INDEX
    Explanations

    email recipients

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

    The neuron strongly activates on numeric literals (i.e. tokens that are 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
    、「
    -1.62
    {"
    -1.39
    ("
    -1.36
     ("
    -1.36
     (“
    -1.35
     “
    -1.30
    ]["
    -1.28
     "
    -1.28
     "<
    -1.25
    　「
    -1.24
    POSITIVE LOGITS
     '
    2.06
    、『
    1.97
     ‘
    1.97
    ='
    1.87
    『
    1.86
     '[
    1.73
    ('
    1.70
     '(
    1.55
    。『
    1.49
    $('#
    1.45
    Activations Density 0.086%

    No Known Activations