© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 73227
    Prev
    Next
    INDEX
    Explanations

    API request paths

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

    This neuron activates on code tokens that specify HTTP endpoint routes (e.g. path strings in Route attributes, URL paths, HTTP method declarations).

    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
     estimés
    -0.93
    などが
    -0.92
     duong
    -0.91
     zwi
    -0.90
     spune
    -0.88
    痰
    -0.87
    hich
    -0.86
     nép
    -0.85
    ülerin
    -0.85
    IBLIO
    -0.84
    POSITIVE LOGITS
    sufficiency
    1.00
     to
    0.99
    viewpager
    0.96
    weł
    0.96
     sweatshirt
    0.96
    elten
    0.96
    ilités
    0.95
    laterra
    0.93
    irected
    0.92
    顷
    0.92
    Activations Density 0.002%

    No Known Activations