© 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. 58882
    Prev
    Next
    INDEX
    Explanations

    githubusercontent.com URLs

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

    This neuron detects GitHub URLs (e.g. raw.githubusercontent.com or gist.github.com links).

    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
     fairest
    -0.79
     oyn
    -0.75
     constructi
    -0.74
     레이
    -0.73
    icity
    -0.70
     Passo
    -0.69
     Kuk
    -0.69
    Haley
    -0.68
    μαστε
    -0.68
    theria
    -0.67
    POSITIVE LOGITS
     coincident
    0.71
    cruz
    0.67
     suelos
    0.66
    蠍
    0.65
    roli
    0.65
    would
    0.64
    laka
    0.63
    NOO
    0.63
    瀑
    0.63
     presentada
    0.62
    Activations Density 0.057%

    No Known Activations