© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 116618
    Prev
    Next
    INDEX
    Explanations

    states and their complements

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

    This neuron detects words (in Portuguese) that signal a request for “how to” or a method/way of doing something (e.g. maneira, forma, ideia, gostar).

    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
     descuentos
    -1.09
     französische
    -1.06
     gravidanza
    -1.05
     câteva
    -1.02
    .³
    -1.00
     entrenar
    -0.98
     fatiga
    -0.98
     anderes
    -0.97
     tambi
    -0.96
     aislada
    -0.96
    POSITIVE LOGITS
     of
    7.97
    of
    2.33
    ของ
    2.31
     Of
    2.05
     của
    1.95
    Of
    1.78
     של
    1.74
     to
    1.69
    もちろん
    1.38
    ของคุณ
    1.38
    Activations Density 0.091%

    No Known Activations