© 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. 84636
    Prev
    Next
    INDEX
    Explanations

    with you

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

    The neuron strongly activates on the Chinese character “带” (as used in phrases like “带您…” or “带前缀…”).

    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
    菹
    -3.00
    ان
    -2.72
     și
    -2.72
    ୈ
    -2.64
    횃
    -2.63
    ه
    -2.58
    ౧
    -2.56
    Ꮴ
    -2.47
    鹟
    -2.45
     Что
    -2.44
    POSITIVE LOGITS
    -
    3.08
     is
    2.69
     were
    2.50
    end
    2.44
     of
    2.30
     contain
    2.20
    你就
    2.20
    了一
    2.17
    be
    2.16
     been
    2.14
    Activations Density 0.002%

    No Known Activations