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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 6996
    Prev
    Next
    INDEX
    Explanations

    `xpath` or `.`

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

    The neuron is looking for numeric tokens (sequences of digits) in the text.

    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
     prismatic
    -0.73
     Yel
    -0.69
     vehículos
    -0.68
     HttpContext
    -0.67
    CDU
    -0.67
    jumper
    -0.67
    disciplinar
    -0.67
    TUT
    -0.66
     основе
    -0.66
    TOL
    -0.65
    POSITIVE LOGITS
    Dave
    0.72
     Dave
    0.72
    选择
    0.70
    Ｃ
    0.70
    abb
    0.69
     Truck
    0.69
    Reentrant
    0.69
    Love
    0.68
     Claire
    0.68
    beforeEach
    0.68
    Activations Density 0.076%

    No Known Activations