© 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. 22-GEMMASCOPE-RES-131K
    4. 98466
    Prev
    Next
    INDEX
    Explanations

    vectors and code

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

    The neuron activates on specialized technical or scientific terminology (e.g. domain‐specific jargon in math and engineering 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
     выбор
    -0.95
     resultado
    -0.94
    ENNE
    -0.92
     результат
    -0.91
    ença
    -0.91
    ộc
    -0.91
    歌手
    -0.91
     внимание
    -0.90
    Πε
    -0.90
    formik
    -0.90
    POSITIVE LOGITS
     it
    1.18
    際には
    0.89
    owohl
    0.89
     hacían
    0.86
     pregunt
    0.84
     urged
    0.80
    場所で
    0.79
    曩
    0.79
    Воспитатель
    0.79
    そうで
    0.79
    Activations Density 0.083%

    No Known Activations