© 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. 78383
    Prev
    Next
    INDEX
    Explanations

    code class definitions and migrations

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

    The main thing this neuron does is detect numeric tokens (digits and numbers) in code.

    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
     模拟
    -0.85
    libat
    -0.81
     支援
    -0.81
    máy
    -0.80
     IConfiguration
    -0.78
     対策
    -0.76
    lıkla
    -0.76
    successor
    -0.75
    enaire
    -0.73
     serupa
    -0.73
    POSITIVE LOGITS
     initial
    1.57
     add
    1.39
     Add
    1.30
     Initial
    1.29
    Initial
    1.25
    Add
    1.19
    add
    1.17
     init
    1.17
    最初
    1.14
     initially
    1.13
    Activations Density 0.006%

    No Known Activations