© 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. 65953
    Prev
    Next
    INDEX
    Explanations

    org/ or regional skin or Randy O or Pages or Q:

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

    The neuron is detecting parts of web addresses (URLs), especially domain names and their punctuation (e.g. “.org”, “/”, etc.).

    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
    !
    -0.92
    ַּ
    -0.90
     грома
    -0.88
     enää
    -0.80
    洗面
    -0.79
     «
    -0.76
    %+
    -0.74
     entweder
    -0.73
     big
    -0.73
    
    -0.72
    POSITIVE LOGITS
    rade
    0.99
     lucu
    0.91
     hopefully
    0.91
    ׇ
    0.90
    oudre
    0.88
    روه
    0.86
    duo
    0.86
     nuove
    0.85
    givings
    0.84
     pide
    0.84
    Activations Density 0.000%

    No Known Activations