© 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. 98743
    Prev
    Next
    INDEX
    Explanations

    UI visibility and layout code

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

    The neuron fires on numeric literals embedded in code (i.e. standalone numbers).

    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
    𒀭
    -0.81
    cshtml
    -0.80
    🎬
    -0.77
     SqlParameter
    -0.76
     schließt
    -0.75
    NESS
    -0.75
     desmotiv
    -0.73
    SqlParameter
    -0.73
    ϭ
    -0.73
    ▩
    -0.73
    POSITIVE LOGITS
     View
    1.27
    View
    1.16
     view
    1.04
    ී
    0.88
     invisible
    0.88
     VIS
    0.83
     invis
    0.81
     visible
    0.81
     Invisible
    0.79
     gone
    0.79
    Activations Density 0.001%

    No Known Activations