© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 39947
    Prev
    Next
    INDEX
    Explanations

    electrical current

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

    The neuron flags specialized, multi-word technical jargon (especially compound terms) typical of antenna and microwave engineering.

    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
    idated
    -1.37
     تلك
    -1.22
     ไม่
    -1.22
     системы
    -1.21
     improvements
    -1.21
    ︲
    -1.20
     patrie
    -1.17
     عدة
    -1.17
     issue
    -1.16
    hability
    -1.16
    POSITIVE LOGITS
     with
    1.55
     sepenuhnya
    1.55
     each
    1.43
    aucune
    1.36
    Each
    1.27
     Each
    1.26
    atnya
    1.24
     ڤ
    1.23
    pæ
    1.23
    évêque
    1.21
    Activations Density 0.152%

    No Known Activations