© 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. 45158
    Prev
    Next
    INDEX
    Explanations

    copyright mentions preceding "by"

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

    The neuron consistently fires on the single-character Russian preposition “в” (i.e. “in”).

    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
    e
    -3.95
    2
    -3.33
    1
    -3.13
    t
    -2.95
    0
    -2.94
    h
    -2.91
    3
    -2.84
    c
    -2.77
    d
    -2.70
    6
    -2.67
    POSITIVE LOGITS
    詎
    2.77
    nessy
    2.77
    
    2.70
    ()<<
    2.61
    
    2.58
     素人
    2.58
     אבל
    2.56
    ériale
    2.55
    ⩴
    2.50
     lenguaje
    2.48
    Activations Density 0.002%

    No Known Activations