© 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. 42570
    Prev
    Next
    INDEX
    Explanations

    academic subjects and professional fields

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

    The neuron flags mentions of academic or technical disciplines (e.g. biomedical engineering, physics, mathematics, nursing, computer science, epidemiology, 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
     that
    -2.41
     on
    -1.31
     each
    -1.23
     võ
    -1.20
    Кон
    -1.19
    Some
    -1.17
    henden
    -1.16
    ANCED
    -1.16
    லை
    -1.16
     EVERY
    -1.15
    POSITIVE LOGITS
     of
    1.41
    //};
    1.22
     programs
    1.22
    five
    1.20
     mengerti
    1.19
    if
    1.17
    nother
    1.17
     März
    1.15
    formatics
    1.14
     trev
    1.14
    Activations Density 0.107%

    No Known Activations