© 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. 22-GEMMASCOPE-RES-131K
    7. 66407
    Prev
    Next
    INDEX
    Explanations

    Russian verb endings and code

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

    The neuron fires on Russian verb forms (roots and common inflections).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     it
    -2.05
     if
    -1.76
     will
    -1.75
     or
    -1.69
     there
    -1.66
     encontré
    -1.64
     would
    -1.63
     anschließend
    -1.63
     could
    -1.59
     when
    -1.59
    POSITIVE LOGITS
     joão
    1.68
     ônibus
    1.65
     xadrez
    1.62
     pyta
    1.60
     nô
    1.60
     tênis
    1.57
     Justiça
    1.56
     kokos
    1.52
     från
    1.51
     então
    1.51
    Activations Density 0.017%

    No Known Activations