© 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. 48180
    Prev
    Next
    INDEX
    Explanations

    после слова

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

    This neuron detects Russian words in specific inflected case endings (e.g. adjective or noun forms ending in “-ому,” “-ом,” “-ем,” etc.).

    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
    ;
    -3.09
    is
    -2.70
    To
    -2.63
    0
    -2.55
    or
    -2.48
    .......
    -2.42
    ........
    -2.41
    鏨
    -2.36
    ......
    -2.34
    and
    -2.30
    POSITIVE LOGITS
    獃
    2.83
    翃
    2.66
    釤
    2.59
    汭
    2.56
    慥
    2.56
    虓
    2.47
    珧
    2.47
    祼
    2.42
    瘣
    2.38
     zeigte
    2.33
    Activations Density 0.003%

    No Known Activations