© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74723
    Prev
    Next
    INDEX
    Explanations

    that or тех

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

    This neuron detects occurrences of the Russian conditional phrase “(в) том случае” (literally “in that case”), often used in “only in that case if…” constructions.

    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
    龃
    -2.03
    猡
    -1.87
    戆
    -1.81
    螄
    -1.80
     recém
    -1.75
    釓
    -1.74
    蛲
    -1.73
     OGSÅ
    -1.70
    鹪
    -1.70
    鹀
    -1.68
    POSITIVE LOGITS
     that
    2.81
    ’
    2.02
     who
    1.98
     with
    1.81
     he
    1.79
    —
    1.77
     you
    1.76
     people
    1.75
    zelfde
    1.73
     what
    1.70
    Activations Density 0.003%

    No Known Activations