© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 75693
    Prev
    Next
    INDEX
    Explanations

    .py files and settings

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

    The neuron detects mentions of configuration and settings-related identifiers in code (e.g. “settings,” “config,” “import” in settings.py or conf files).

    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
    舛
    -0.81
    敤
    -0.75
    ניק
    -0.74
    パソコン
    -0.72
     senaste
    -0.72
     adri
    -0.71
     cancels
    -0.71
    調整
    -0.70
    樋
    -0.70
     engravings
    -0.69
    POSITIVE LOGITS
    MEDIA
    1.12
     MEDIA
    1.09
     installed
    0.98
     settings
    0.90
     media
    0.87
    installed
    0.84
     installation
    0.83
    vre
    0.82
    getattr
    0.81
    ᴗ
    0.81
    Activations Density 0.007%

    No Known Activations