© 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. 10-GEMMASCOPE-RES-131K
    7. 127195
    Prev
    Next
    INDEX
    Explanations

    Chinese nouns and English prepositions, adjectives and proper nouns

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

    The neuron responds to uncommon or low‐frequency content words (e.g. “nigh,” “favored,” Chinese terms like “稍,” “必要,” “态度,” 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_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
     recently
    -1.76
    蹋
    -1.70
     anteriormente
    -1.70
    ჱ
    -1.66
     soon
    -1.66
     recientemente
    -1.63
    还不错
    -1.63
    錮
    -1.60
    玏
    -1.59
    をも
    -1.58
    POSITIVE LOGITS
     була
    1.59
    劻
    1.58
    en
    1.58
    ンダイ
    1.55
     seguinte
    1.51
     advertencia
    1.50
    nons
    1.48
    Жизнь
    1.46
    ين
    1.45
     skriver
    1.45
    Activations Density 0.003%

    No Known Activations