© 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. 7035
    Prev
    Next
    INDEX
    Explanations

    http links, file extensions, code snippets

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

    This neuron activates on fragments of URLs or web addresses (domains, paths, and protocol separators).

    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
    全程
    -0.72
     agent
    -0.70
    Катего
    -0.69
    apeno
    -0.69
    mol
    -0.68
     Así
    -0.67
    願い
    -0.67
    OUNTS
    -0.66
    priv
    -0.66
    LOY
    -0.66
    POSITIVE LOGITS
     langit
    0.77
    methodName
    0.69
    ．
    0.68
    PVC
    0.66
    (
    0.66
    сми
    0.66
    BETH
    0.66
     ESP
    0.65
    Abbas
    0.64
    auré
    0.64
    Activations Density 0.059%

    No Known Activations