© 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. 22-GEMMASCOPE-RES-131K
    7. 71502
    Prev
    Next
    INDEX
    Explanations

    internet addresses

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

    The neuron fires on URL components (e.g. “http”, “://”, “.com”, “.org”, “.edu” etc.), effectively detecting web addresses.

    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
     vorhandenen
    -1.16
     què
    -1.14
     vorbere
    -1.13
     vorhand
    -1.11
     wöch
    -1.09
     llevará
    -1.08
     umfang
    -1.05
    お部屋
    -1.04
     genügend
    -1.04
     zusätz
    -1.03
    POSITIVE LOGITS
    )
    1.24
    锱
    1.13
     ._
    1.10
    😲
    1.09
    😱
    1.08
     which
    1.08
    🎃
    1.05
    🤯
    1.03
    ʿ
    1.03
    🤬
    1.02
    Activations Density 0.053%

    No Known Activations