© 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. 34-GEMMASCOPE-RES-131K
    7. 77694
    Prev
    Next
    INDEX
    Explanations

    access modifiers: private, internal

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

    The neuron detects documentation‐style annotation tokens (e.g. comment markers and “@” tags) in 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_34/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
     perbuatan
    -0.86
    าก็
    -0.80
     alternativ
    -0.78
     φυσ
    -0.77
    ellemző
    -0.76
     manqué
    -0.76
    みんなの
    -0.75
    均衡
    -0.74
    ンスター
    -0.73
     男孩
    -0.73
    POSITIVE LOGITS
     internal
    2.55
    internal
    2.31
    内部
    2.00
     private
    1.97
    INTERNAL
    1.93
     Internal
    1.89
     INTERNAL
    1.80
    Internal
    1.78
    私
    1.73
    private
    1.70
    Activations Density 0.056%

    No Known Activations