© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15410
    Prev
    Next
    INDEX
    Explanations

    code documentation comments

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

    The neuron fires on the appearance of the word “brief” (as in code‐documentation comment tags like “\brief” or “@brief”).

    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
     aqueles
    -1.76
     geschützt
    -1.63
     recientemente
    -1.53
     aquele
    -1.53
     verdaderamente
    -1.50
     geleverd
    -1.42
     beträ
    -1.41
     gezet
    -1.41
     aquellos
    -1.41
     serão
    -1.38
    POSITIVE LOGITS
     Should
    1.68
     which
    1.48
     about
    1.34
     نک
    1.27
     Appetit
    1.26
    ⫽
    1.26
     How
    1.26
     how
    1.25
    }(
    1.21
    }=\
    1.21
    Activations Density 0.061%

    No Known Activations