© 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. 15883
    Prev
    Next
    INDEX
    Explanations

    Agoda, Jumia, Eureka, Car, If

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

    The neuron activates on substrings of commercial website domain names (e.g. “Agoda,” “.com,” “Jumia”).

    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
     like
    -1.29
    ?
    -1.16
    </h2>
    -1.15
    bedien
    -1.14
     уход
    -1.13
    "
    -1.13
    /
    -1.13
     сотрудники
    -1.12
     Commentaires
    -1.09
    =
    -1.05
    POSITIVE LOGITS
    ஔ
    1.25
     Hinsicht
    1.16
     indicó
    1.11
    viembre
    1.10
     Vorbereitung
    1.06
     welche
    1.05
    Ferdin
    1.05
    kta
    1.05
    沌
    1.05
    くれました
    1.04
    Activations Density 0.000%

    No Known Activations