© 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. 66009
    Prev
    Next
    INDEX
    Explanations

    Pulmonary stenosis

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

    tokens within code or structured data files, particularly detecting elements in configuration files with high activation on indentation, brackets, and syntax elements.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron is activated by numeric tokens (digits and sequences of digits, including version numbers and other numbers).

    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
     it
    -1.95
     this
    -1.80
     your
    -1.76
    ^(@
    -1.75
    sourceforge
    -1.67
    击败
    -1.60
    mycompany
    -1.59
     adequada
    -1.59
     our
    -1.58
    richTextBox
    -1.56
    POSITIVE LOGITS
     fået
    1.70
     is
    1.70
     chrétien
    1.69
    However
    1.59
    Those
    1.50
     namun
    1.46
     religieux
    1.45
    футбо
    1.44
     évêque
    1.44
     Nevertheless
    1.43
    Activations Density 0.037%

    No Known Activations