© 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. 10-GEMMASCOPE-RES-131K
    7. 130586
    Prev
    Next
    INDEX
    Explanations

    Lie groups and algebras

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

    The neuron fires on specialized mathematical terminology (e.g. names of structures like “manifold,” “Grassmannian,” “group,” “varieties,” “Bruhat order,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ;
    -1.41
    addField
    -1.25
    Amp
    -1.20
    ]];
    -1.19
    ?
    -1.17
     brilliant
    -1.16
    aria
    -1.14
     important
    -1.14
    onomian
    -1.14
    section
    -1.13
    POSITIVE LOGITS
    嚭
    1.19
    媄
    1.13
    钎
    1.13
    SCIENCE
    1.11
    RODUCTION
    1.11
     óptica
    1.09
    втра
    1.09
    shadows
    1.06
    zaSy
    1.06
     Foreword
    1.05
    Activations Density 0.058%

    No Known Activations