© 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. 34-GEMMASCOPE-RES-131K
    7. 31717
    Prev
    Next
    INDEX
    Explanations

    verb roots and conjugations

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

    This neuron detects Russian question phrases, especially the “в чём/в чем” (“in what”) construction.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     keperluan
    -0.93
    Več
    -0.93
     kenaikan
    -0.91
    RemindMe
    -0.90
     peningkatan
    -0.89
     soltar
    -0.89
    Tahun
    -0.86
    sepatu
    -0.84
    tutup
    -0.84
     íntima
    -0.83
    POSITIVE LOGITS
     are
    2.75
     were
    1.98
     aren
    1.47
    are
    1.46
     weren
    1.27
     seront
    1.16
     poden
    1.07
     должен
    1.06
    were
    1.02
     ARE
    1.01
    Activations Density 0.023%

    No Known Activations