© 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. 102767
    Prev
    Next
    INDEX
    Explanations

    Russian and Latvian grammatical endings

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

    The neuron flags proper‐noun tokens—names of people, places, organizations, dates, and similar multilingual named entities.

    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
     confronti
    -1.89
     were
    -1.88
     sogni
    -1.82
     Anche
    -1.70
     οπο
    -1.70
     efforts
    -1.69
    鹇
    -1.68
    ે
    -1.65
    踯
    -1.63
     объ
    -1.61
    POSITIVE LOGITS
    to
    1.71
    ↵↵
    1.70
     l
    1.52
    ekš
    1.43
    етка
    1.41
      
    1.38
    —”
    1.38
    افی
    1.37
    d
    1.36
    。
    1.36
    Activations Density 0.072%

    No Known Activations