© 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. 129467
    Prev
    Next
    INDEX
    Explanations

    Appellant or appellee

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

    The neuron activates on preprocessor pragma directives (e.g. “#pragma mark –”) in source-code comments.

    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
    With
    -3.06
    From
    -3.03
    when
    -3.02
    When
    -2.88
    Before
    -2.86
    Not
    -2.80
    Just
    -2.75
    ם
    -2.73
    Here
    -2.73
    )’
    -2.72
    POSITIVE LOGITS
    鹛
    2.83
     dreary
    2.73
     -
    2.70
     '
    2.69
    辄
    2.64
     stalwart
    2.55
    狨
    2.52
    的就
    2.48
    甚至是
    2.47
    𝒔
    2.47
    Activations Density 0.158%

    No Known Activations