© 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. 10-GEMMASCOPE-RES-131K
    7. 44311
    Prev
    Next
    INDEX
    Explanations

    Russian verb suffixes and endings

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

    The neuron fires on Russian infinitive verbs (especially those ending in –овать/–ировать).

    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
    或
    -2.55
    2
    -2.55
    或者
    -2.53
    那个
    -2.48
    是
    -2.47
    
    -2.41
    或是
    -2.38
     remarkably
    -2.36
     VERY
    -2.28
    
    -2.27
    POSITIVE LOGITS
     crudo
    2.34
    ⢫
    2.27
    趼
    2.14
    鉝
    2.09
    —”
    2.08
    鱘
    2.06
    鈊
    2.06
    ––––
    2.05
    rainian
    2.05
    酩
    2.02
    Activations Density 0.005%

    No Known Activations