© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10899
    Prev
    Next
    INDEX
    Explanations

    elements and components

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

    The neuron activates on occurrences of the word “element” (and its plural forms) in either English (“elements”) or Russian (“элементы”/“элемента”).

    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
    ↵
    -2.23
     短发
    -2.03
     Our
    -2.03
    0
    -2.02
     totalement
    -1.97
     itſelf
    -1.97
     divertente
    -1.89
    箝
    -1.89
     dicono
    -1.86
     eenige
    -1.84
    POSITIVE LOGITS
    珦
    2.66
     elemento
    2.34
    他对
    2.28
    汌
    2.17
    垍
    2.08
     perdido
    2.05
    ྕ
    1.97
     –
    1.97
     For
    1.95
    ・「
    1.93
    Activations Density 0.019%

    No Known Activations