© 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. 10-GEMMASCOPE-RES-131K
    7. 87285
    Prev
    Next
    INDEX
    Explanations

    ending suffixes in Slavic languages

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

    The neuron strongly activates on Russian/Ukrainian number words (cardinals and ordinals).

    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
     {
    -2.16
     \'
    -1.70
    ia
    -1.69
    on
    -1.65
    9
    -1.64
    ity
    -1.59
     and
    -1.59
    type
    -1.55
    A
    -1.55
    at
    -1.53
    POSITIVE LOGITS
     .”
    1.99
    ).”
    1.98
     that
    1.84
    ريعة
    1.82
    ..”
    1.80
    ↵↵
    1.78
    )”
    1.78
    ;”
    1.75
    懨
    1.68
     will
    1.67
    Activations Density 0.026%

    No Known Activations