© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 423
    Prev
    Next
    INDEX
    Explanations

    rising edge-triggered

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

    The neuron fires on code‐style tokens—especially uppercase, underscore-separated identifiers, numeric literals, and related syntax used in C/C++ declarations.

    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
    linalg
    -0.74
    itum
    -0.72
    mund
    -0.69
    ologous
    -0.68
    的情況
    -0.68
    anim
    -0.66
    幺
    -0.66
    组成
    -0.66
    lub
    -0.66
     fate
    -0.65
    POSITIVE LOGITS
     rising
    2.56
     Rising
    2.13
     edge
    2.08
    Rising
    1.95
     edges
    1.85
    rising
    1.84
     rise
    1.84
     Edge
    1.77
    edge
    1.72
    edges
    1.72
    Activations Density 0.029%

    No Known Activations