© 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. 129528
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on numeric literals (numbers) in code snippets.

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

    code blocks and programming function calls

    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
    rzez
    -0.83
    beeren
    -0.82
    acyjnych
    -0.81
    Твор
    -0.81
     terminus
    -0.79
     lửa
    -0.79
    楽しみ
    -0.78
    entation
    -0.77
    Termin
    -0.75
    seit
    -0.75
    POSITIVE LOGITS
    玉
    0.89
     Conditioner
    0.88
    具
    0.78
    lotz
    0.77
     wiem
    0.77
    nitzer
    0.75
    情节
    0.75
     corse
    0.75
     كور
    0.74
     now
    0.73
    Activations Density 0.014%

    No Known Activations