© 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. 10-GEMMASCOPE-RES-131K
    7. 20880
    Prev
    Next
    INDEX
    Explanations

    base url or URI

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

    The neuron activates on code identifiers and constants referring to base URLs (e.g. “baseUrl”, “BASE_URL”, “apiHost” 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_10/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
    Џ
    -1.75
     flechas
    -1.74
     fábricas
    -1.74
     estancias
    -1.70
     that
    -1.65
     virtudes
    -1.65
     various
    -1.63
     localidades
    -1.62
    начала
    -1.60
    汌
    -1.60
    POSITIVE LOGITS
     ander
    1.61
    ’
    1.60
    再也
    1.52
     bougies
    1.50
    
    1.46
     этих
    1.41
    这么
    1.41
     eau
    1.41
     immen
    1.41
     europa
    1.37
    Activations Density 0.012%

    No Known Activations