© 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. 34-GEMMASCOPE-RES-131K
    7. 93176
    Prev
    Next
    INDEX
    Explanations

    names of places and people from various countries

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

    This neuron detects tokens containing non-ASCII characters—especially Slavic/central European diacritics.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    Funktionen
    -0.96
    盞
    -0.87
     promesse
    -0.85
     funzioni
    -0.84
    鸵
    -0.83
     istruzioni
    -0.83
     Trennung
    -0.82
     descente
    -0.81
    Estructura
    -0.80
     함께
    -0.79
    POSITIVE LOGITS
    路径
    0.80
    theoremstyle
    0.79
     любые
    0.79
    ediat
    0.77
    ANAL
    0.77
    很多
    0.76
     poderos
    0.76
    лә
    0.76
    phylaxis
    0.76
    ご購入
    0.75
    Activations Density 0.003%

    No Known Activations