© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 111105
    Prev
    Next
    INDEX
    Explanations

    programming instance and class constructs

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

    The neuron strongly activates on programming‐language keywords, pragmas, type names, and other code identifiers (e.g. all‐caps or CamelCase tokens).

    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
     Tend
    -0.82
    seli
    -0.77
     FAIR
    -0.75
    ctypes
    -0.75
    ortment
    -0.72
     descrip
    -0.72
     fairing
    -0.72
     sunburn
    -0.71
     transférez
    -0.71
     indign
    -0.70
    POSITIVE LOGITS
     instance
    0.99
     instances
    0.98
     dispatch
    0.97
    Instances
    0.90
     generic
    0.88
    instance
    0.87
     registry
    0.85
    dispatch
    0.85
     registered
    0.82
    instances
    0.78
    Activations Density 0.065%

    No Known Activations