© 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. 22-GEMMASCOPE-RES-131K
    4. 587
    Prev
    Next
    INDEX
    Explanations

    urls and links

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

    The neuron activates on parts of web addresses (URL components such as “https://”, domain names, paths, and social‐media 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_22/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
     any
    -1.18
     these
    -1.08
     μόνο
    -1.07
    osó
    -1.00
     проє
    -0.98
     both
    -0.98
     Fußballspieler
    -0.98
     anything
    -0.95
     medication
    -0.94
     whatever
    -0.92
    POSITIVE LOGITS
     forskjellige
    1.12
    😙
    1.01
     Undang
    0.96
     Tomáš
    0.94
    паси
    0.91
    Cze
    0.90
    传感器
    0.90
    ☓
    0.90
    😗
    0.90
    😲
    0.89
    Activations Density 0.013%

    No Known Activations