© 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. 83859
    Prev
    Next
    INDEX
    Explanations

    wizard completion or setup

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

    The neuron fires strongly on programming‐style identifiers—especially CamelCase class, method, or API names and their component tokens.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    technical documentation and code related to user interface elements, configuration settings, and software preferences.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    instructions and terminology for software GUI setup/configuration, especially IDE wizard pages, preferences panels, and menu-driven actions.

    oai_token-act-pair · gpt-5Triggered 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
    Secured
    -0.75
    GAT
    -0.71
    Compare
    -0.69
    vák
    -0.69
    Alarm
    -0.68
    gation
    -0.68
     ピン
    -0.68
    Boom
    -0.67
     pop
    -0.67
    menu
    -0.66
    POSITIVE LOGITS
     wizard
    1.46
     Finish
    1.27
     finish
    1.27
     FINISH
    1.18
     Wizard
    1.18
    Finish
    1.15
     wizards
    1.13
    finish
    1.10
    Wizard
    1.09
    FINISH
    1.09
    Activations Density 0.042%

    No Known Activations