© 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. 22-GEMMASCOPE-RES-131K
    7. 73036
    Prev
    Next
    INDEX
    Explanations

    code comments in multiple languages

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

    The neuron is picking up on block‐comment text (especially Javadoc‐style comments and their closing “*/” markers) in source code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    pejo
    -1.11
     anstatt
    -1.05
    lliant
    -1.05
     步骤
    -1.04
     tradicionales
    -1.03
    ochial
    -1.02
     electric
    -1.02
    YSQL
    -1.01
     offizi
    -1.01
    点点头
    -0.98
    POSITIVE LOGITS
    了下
    0.98
     responsab
    0.94
    のエ
    0.88
    (!__
    0.87
    haltens
    0.86
     moest
    0.85
     fantastique
    0.85
     Alternatives
    0.85
    beispiel
    0.85
    Ingrid
    0.84
    Activations Density 0.025%

    No Known Activations