© 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. 34-GEMMASCOPE-RES-131K
    7. 90219
    Prev
    Next
    INDEX
    Explanations

    Russian and Slavic words

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

    The neuron strongly activates on the two‐letter token “go” (or its Cyrillic equivalent “Го”), i.e. instances of “go” as a standalone token.

    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
    顺利
    -0.86
     guardia
    -0.85
    gie
    -0.82
    家を
    -0.79
     démarche
    -0.79
     EdgeInsets
    -0.77
     faut
    -0.76
    その
    -0.76
     خوش
    -0.75
    moment
    -0.75
    POSITIVE LOGITS
     väljer
    0.90
     virš
    0.90
     assolu
    0.88
    為に
    0.83
     potrzebu
    0.82
     pubblici
    0.82
     знаешь
    0.82
     zarówno
    0.82
     altrett
    0.81
    の準備
    0.81
    Activations Density 0.004%

    No Known Activations