© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 67413
    Prev
    Next
    INDEX
    Explanations

    foreign languages

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

    The neuron is keyed into subjective or evaluative language—words that express opinion or emotional commentary.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ଶ
    -1.73
     получите
    -1.64
    大军
    -1.51
    constexpr
    -1.45
    اقرأ
    -1.38
     vérité
    -1.34
    かも知
    -1.34
     nocturne
    -1.30
     باشی
    -1.30
     dévelo
    -1.29
    POSITIVE LOGITS
     различни
    1.52
    Mengapa
    1.34
     повече
    1.34
     всички
    1.32
     çünkü
    1.32
    Kenapa
    1.31
    我想
    1.31
     Könige
    1.30
    nější
    1.26
    Bagaimana
    1.25
    Activations Density 0.043%

    No Known Activations