© 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. 22-GEMMASCOPE-RES-131K
    7. 68959
    Prev
    Next
    INDEX
    Explanations

    papers and books titles

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

    The neuron is activated by words that are part of publication or citation metadata—journal, conference, book, or proceedings titles.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    れています
    -1.04
     Dateien
    -0.99
     Ebenen
    -0.96
     Funktionalität
    -0.95
     Einstellungen
    -0.94
    唛
    -0.94
     angegebenen
    -0.93
     Komponenten
    -0.92
     Bearbeitung
    -0.91
    相手
    -0.90
    POSITIVE LOGITS
     internationaux
    1.16
    ʹ
    1.04
     parfois
    1.03
    okkal
    1.02
     требует
    1.01
    三菱
    0.99
    шня
    0.98
     souvent
    0.97
    restling
    0.95
     européens
    0.95
    Activations Density 0.006%

    No Known Activations