© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44923
    Prev
    Next
    INDEX
    Explanations

    list item or entry

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

    This neuron fires on words referring to individual elements in a collection or UI list (e.g. “item,” “items,” “entry”).

    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
    .
    -1.82
    ”、“
    -1.24
    still
    -1.13
    ,”
    -1.12
    ņa
    -1.12
     rett
    -1.11
    。“
    -1.09
     чтобы
    -1.09
     rouges
    -1.09
    always
    -1.08
    POSITIVE LOGITS
     that
    1.61
     Поэтому
    1.55
    áln
    1.47
     pembeli
    1.45
     about
    1.44
    ípio
    1.40
     Therefore
    1.32
    赑
    1.31
    璟
    1.31
    楽しかった
    1.27
    Activations Density 0.142%

    No Known Activations