© 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. 10-GEMMASCOPE-RES-131K
    7. 60179
    Prev
    Next
    INDEX
    Explanations

    using statements

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

    This neuron detects numeric version tokens (e.g. “450”, “482”, “486”) that appear after “System.” in using/import 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_10/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
    "
    -2.22
    '
    -1.79
     épisodes
    -1.67
     hugely
    -1.66
    _
    -1.66
     "
    -1.64
     lauded
    -1.62
     logements
    -1.59
     bedeckt
    -1.59
    了一会儿
    -1.57
    POSITIVE LOGITS
    に行ってきました
    2.00
     and
    1.97
    劻
    1.81
     in
    1.61
    Even
    1.45
     delgada
    1.45
    ↵↵
    1.45
    焄
    1.42
    </b>
    1.42
     vitamina
    1.41
    Activations Density 0.007%

    No Known Activations