© 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. 27827
    Prev
    Next
    INDEX
    Explanations

    dart, package, hpp, Original

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

    The neuron strongly activates on file‐extension tokens (e.g. “dart”, “hpp”, “h”) in import/include statements.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    了一会儿
    -1.48
     to
    -1.45
     también
    -1.41
    中心的
    -1.41
     rique
    -1.41
     ONLY
    -1.40
     EconPapers
    -1.40
     обороны
    -1.38
     their
    -1.34
     because
    -1.33
    POSITIVE LOGITS
    ↵↵
    1.60
     菇
    1.43
     recentemente
    1.41
    2
    1.38
     FUCKING
    1.36
     SILVER
    1.30
     gezondheid
    1.30
    <bos>
    1.30
    3
    1.27
     cunos
    1.27
    Activations Density 0.001%

    No Known Activations