© 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. 2992
    Prev
    Next
    INDEX
    Explanations

    from Russian preposition

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

    The neuron strongly activates on the Russian preposition “из” (in any casing).

    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
    しますが
    -0.79
     Glä
    -0.79
     out
    -0.77
     descent
    -0.74
     Guthrie
    -0.74
    ttä
    -0.73
     steady
    -0.72
    も含
    -0.72
    .-(
    -0.72
    tická
    -0.71
    POSITIVE LOGITS
     balik
    1.01
    ématique
    0.94
     Из
    0.86
    getAll
    0.84
    Prepare
    0.83
     ordina
    0.83
    ogyn
    0.81
    Из
    0.80
    prepare
    0.79
     EXPERIENCE
    0.79
    Activations Density 0.005%

    No Known Activations