© 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. 101614
    Prev
    Next
    INDEX
    Explanations

    Russian words

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

    The neuron detects ellipsis tokens (series of three dots) indicating truncated or continuation text.

    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
    ఽ
    -2.06
     reaſon
    -2.03
     唯美
    -1.95
    despite
    -1.91
    蛱
    -1.90
    
    -1.89
    didn
    -1.88
    睃
    -1.86
     unveils
    -1.86
    蠵
    -1.84
    POSITIVE LOGITS
     even
    2.58
     if
    2.50
     but
    2.13
     at
    2.03
     in
    1.95
     as
    1.95
     can
    1.93
     more
    1.91
     just
    1.90
    ↵
    1.88
    Activations Density 0.007%

    No Known Activations