© 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. 130305
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on standalone numeric tokens (digit strings) in code, i.e. number literals.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    new post creation commands

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Packaged
    -0.83
    v
    -0.83
    etsu
    -0.83
     нарушение
    -0.82
     ممكن
    -0.80
    mls
    -0.80
    Appointments
    -0.79
    当时
    -0.78
    Robots
    -0.77
    nees
    -0.77
    POSITIVE LOGITS
     nuevos
    1.04
     nuevas
    1.01
    aryen
    0.98
     nuevo
    0.98
    辞职
    0.97
    鲢
    0.95
     nuovo
    0.91
     new
    0.91
    giá
    0.90
    podob
    0.89
    Activations Density 0.005%

    No Known Activations