© 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. 15340
    Prev
    Next
    INDEX
    Explanations

    language identification and translation

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

    The neuron activates on Russian (Cyrillic) content tokens.

    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
    p
    -2.16
    1
    -2.06
    al
    -2.00
    ными
    -1.92
    ated
    -1.91
    
    -1.90
     I
    -1.88
    “
    -1.86
    還沒
    -1.84
    hahaha
    -1.83
    POSITIVE LOGITS
    葙
    2.55
    逦
    2.19
     Они
    2.13
    astră
    2.11
     Their
    2.09
     During
    2.08
     οπο
    2.03
    癀
    2.02
     revés
    2.00
     They
    1.99
    Activations Density 0.010%

    No Known Activations