© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110923
    Prev
    Next
    INDEX
    Explanations

    Russian words and Spanish verbs

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

    The neuron flags any token written in a non‐English script or with non‐ASCII characters (i.e. foreign‐language words, diacritics, Cyrillic, 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_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
    чия
    -0.79
     volna
    -0.74
    QSize
    -0.73
    ῾
    -0.73
     pará
    -0.73
    abilità
    -0.72
    $+
    -0.72
    fry
    -0.71
     renom
    -0.71
     院
    -0.71
    POSITIVE LOGITS
    те
    0.82
     çıkan
    0.81
    мость
    0.75
     querían
    0.73
    мс
    0.72
    Carole
    0.71
     ਬ
    0.70
    ーパー
    0.70
     sanitarios
    0.70
     sher
    0.69
    Activations Density 0.024%

    No Known Activations