© 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. 66489
    Prev
    Next
    INDEX
    Explanations

    Spanish greetings and entities

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

    This neuron strongly activates on person names or other proper-name tokens, i.e. named entities.

    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
     on
    -1.18
     våra
    -1.07
     we
    -1.04
    warte
    -1.02
    咂
    -1.02
     so
    -1.01
    ﹔
    -0.97
     schreef
    -0.96
     Europe
    -0.94
    assertThrows
    -0.94
    POSITIVE LOGITS
    ctivas
    1.19
    FUENTES
    1.17
    さてさて
    1.12
    GRACIAS
    1.09
    routeProvider
    1.07
     unn
    1.06
    шил
    1.05
    ➏
    1.05
    manned
    1.04
    gracias
    1.03
    Activations Density 0.001%

    No Known Activations