© 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. 105573
    Prev
    Next
    INDEX
    Explanations

    это + concluding word

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

    The neuron strongly activates on the Russian demonstrative word “это.”

    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
    漚
    -2.89
    騭
    -2.67
    犼
    -2.59
    </td>
    -2.50
    ਃ
    -2.45
    卝
    -2.42
    tività
    -2.42
    鉿
    -2.41
    antry
    -2.39
    <td>
    -2.38
    POSITIVE LOGITS
     ที่
    2.53
    !”
    2.50
     ”
    2.44
     могут
    2.42
     行っ
    2.36
     ซึ่ง
    2.33
     .”
    2.23
     —
    2.23
     を
    2.22
     был
    2.20
    Activations Density 0.002%

    No Known Activations