© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99868
    Prev
    Next
    INDEX
    Explanations

    JennieSilver CaveLOS ANGELESQ

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

    The neuron strongly activates on URL/endpoint and API-style tokens (e.g. “https://…”, domain/path separators, acronyms like FCM, IID, API, and other code-style identifiers).

    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
     ябло
    -0.94
    tiges
    -0.84
    retz
    -0.77
    cheiben
    -0.75
    veis
    -0.75
     judicia
    -0.71
     تیر
    -0.71
    LError
    -0.71
    enzio
    -0.71
    phors
    -0.71
    POSITIVE LOGITS
    getToken
    1.02
    iid
    0.89
     lungs
    0.88
    lungs
    0.87
     token
    0.86
    InstanceId
    0.86
    token
    0.80
    [!
    0.78
     Mei
    0.78
    Topic
    0.78
    Activations Density 0.020%

    No Known Activations