© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 24007
    Prev
    Next
    INDEX
    Explanations

    society meetings journals associations

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

    The neuron detects mentions of academic publication and conference identifiers—journal titles, society names, symposium or meeting names, and their abbreviations.

    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
     who
    -1.32
     almacén
    -1.16
    헷
    -1.15
     sufrido
    -1.12
     comenzado
    -1.12
    ardonnay
    -1.11
     preferencia
    -1.10
    bumptech
    -1.09
    其它
    -1.09
    ISSIPPI
    -1.08
    POSITIVE LOGITS
     such
    1.48
    :&
    1.29
     cerchi
    1.20
     JG
    1.13
    CION
    1.13
    ياً
    1.13
    쨌
    1.12
    רכ
    1.11
     ファイル
    1.11
     uiteindelijk
    1.10
    Activations Density 0.050%

    No Known Activations