© 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. 10-GEMMASCOPE-RES-131K
    7. 19824
    Prev
    Next
    INDEX
    Explanations

    at times

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

    The neuron strongly activates on spans of direct speech—that is, text enclosed in quotation marks.

    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
     infek
    -1.42
     pertanto
    -1.37
    ukunfts
    -1.35
     ottim
    -1.33
     Wissenschaften
    -1.32
    футболка
    -1.30
    alians
    -1.29
    を見つけ
    -1.28
     çocu
    -1.27
     хотели
    -1.27
    POSITIVE LOGITS
     BorderSide
    1.48
    mappedBy
    1.39
     zostały
    1.39
     yesterday
    1.37
     وصلة
    1.36
    MathML
    1.35
     neceffary
    1.34
     another
    1.34
     during
    1.32
    CESO
    1.31
    Activations Density 0.131%

    No Known Activations