© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31005
    Prev
    Next
    INDEX
    Explanations

    sequences containing the

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

    The neuron is detecting numeric literals (sequences of digits) in code and configuration files.

    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
     Men
    -0.64
     règne
    -0.64
    一条
    -0.62
    外部連結
    -0.62
    <0x87>
    -0.61
     wont
    -0.61
     Fo
    -0.61
     pins
    -0.60
     nổi
    -0.60
     Interstate
    -0.59
    POSITIVE LOGITS
    ofthe
    1.28
     the
    1.13
    OfThe
    1.00
     Ihe
    0.88
    ethe
    0.83
    inthe
    0.82
     della
    0.82
    ザ
    0.81
     ofthe
    0.80
    then
    0.77
    Activations Density 2.638%

    No Known Activations