© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99018
    Prev
    Next
    INDEX
    Explanations

    docblock comments

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

    This neuron activates on PHPDoc‐style comment markers (the “/**” openings and leading “*” lines in docblock 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
     dieser
    -1.88
     unserer
    -1.60
     erzeugt
    -1.46
     größer
    -1.46
     Ihrer
    -1.44
     significativo
    -1.44
     competitivo
    -1.41
    俨
    -1.41
    ：……
    -1.38
    頹
    -1.37
    POSITIVE LOGITS
     unique
    1.55
    .~\
    1.46
    rightarrow
    1.42
    يست
    1.41
    我现在
    1.40
    __.
    1.40
     unusual
    1.36
    耑
    1.36
     = 
    1.35
    !***
    1.34
    Activations Density 0.006%

    No Known Activations