© 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. 22-GEMMASCOPE-RES-131K
    7. 66442
    Prev
    Next
    INDEX
    Explanations

    http urls and code snippets

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

    This neuron is triggered by all‐caps identifiers or constants (e.g. environment variable names, macro names, or uppercase tokens).

    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
    StreetMap
    -0.90
    alucía
    -0.90
    ֩
    -0.88
     {\
    -0.84
    یم
    -0.82
    licopter
    -0.82
    TProtocol
    -0.80
    Renderer
    -0.78
    iferous
    -0.78
    をご覧ください
    -0.77
    POSITIVE LOGITS
     Naran
    0.85
     Symmetric
    0.84
    缆
    0.82
    Gg
    0.77
     cajones
    0.76
     Golem
    0.75
    kkar
    0.75
     superman
    0.75
    颀
    0.74
    Kk
    0.74
    Activations Density 0.020%

    No Known Activations