© 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-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 8094
    Prev
    Next
    INDEX
    Explanations

    configuration file keywords

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

    The neuron fires strongly on specific IDE/product identifiers (especially “Visual Studio” and its version–or registry–tokens), i.e. it detects mentions of the Visual Studio environment.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Мат
    0.64
     Elemente
    0.62
    Architecture
    0.56
     Architecture
    0.55
     Саме
    0.55
     王
    0.54
     Generating
    0.54
     요소
    0.54
     वाणी
    0.54
    Processor
    0.54
    POSITIVE LOGITS
     stow
    0.56
    erian
    0.56
    횐
    0.55
     labor
    0.54
     wagons
    0.54
     realtime
    0.53
     ciné
    0.53
     minis
    0.53
     despert
    0.53
     zaměst
    0.53
    Activations Density 0.005%

    No Known Activations