© 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. 34-GEMMASCOPE-RES-131K
    7. 77339
    Prev
    Next
    INDEX
    Explanations

    "role" attribute values

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

    The neuron activates on occurrences of the attribute name “role” (e.g. HTML/ARIA or JSON key/value pairs containing “role”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     multitud
    -0.84
    britanni
    -0.83
    pprint
    -0.77
     Giá
    -0.77
    Glossary
    -0.77
    дки
    -0.77
     Grup
    -0.74
    Mux
    -0.73
     sportif
    -0.71
     proposé
    -0.71
    POSITIVE LOGITS
    一方面
    0.77
     дево
    0.73
    recen
    0.72
    rolla
    0.71
    blas
    0.71
    titu
    0.70
    Rol
    0.69
     passende
    0.68
     regione
    0.68
     Rol
    0.68
    Activations Density 0.016%

    No Known Activations