© 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. 102857
    Prev
    Next
    INDEX
    Explanations

    Doug McIntosh / Economical

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

    The neuron flags tokens that are part of R/Shiny code—especially Shiny function names, UI component calls, and library imports.

    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
     refin
    -0.83
     بسي
    -0.80
    ateria
    -0.79
    NOVA
    -0.79
    leson
    -0.78
     damn
    -0.78
    стый
    -0.76
    సం
    -0.72
     Covington
    -0.70
    :]:
    -0.69
    POSITIVE LOGITS
     Dash
    1.13
    Dash
    1.09
     dash
    1.09
    dash
    0.97
     Азербай
    0.86
     Azerbaijan
    0.85
    dcc
    0.84
     enfants
    0.84
    children
    0.84
    Дина
    0.84
    Activations Density 0.013%

    No Known Activations