© 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. 13310
    Prev
    Next
    INDEX
    Explanations

    invoked, upon, called, forth, Into

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

    The neuron flags instances of “invoke” or its synonyms (e.g. “invoke,” “invoked,” “summoning,” “calling up”) in various contexts.

    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
     agujeros
    -1.23
     neumáticos
    -1.09
     tornillos
    -1.06
     soportes
    -1.06
     trámites
    -1.03
     rehabilitación
    -1.01
     sustituir
    -1.01
     gratuitas
    -1.01
     asegurarse
    -0.97
     появилась
    -0.97
    POSITIVE LOGITS
     to
    2.11
     help
    1.45
     from
    1.41
     more
    1.13
     memories
    1.12
    ISHMENT
    1.11
    resources
    1.11
     diverse
    1.05
     publié
    1.05
     Both
    1.03
    Activations Density 0.058%

    No Known Activations