© 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. 10-GEMMASCOPE-RES-131K
    4. 20429
    Prev
    Next
    INDEX
    Explanations

    Non-English words followed by specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    锨
    -2.42
     you
    -2.36
    ⸥
    -2.13
    ⚋
    -2.11
    ⎔
    -2.09
     famed
    -2.08
    鲩
    -2.05
     preferências
    -2.03
     of
    -1.98
     ANOTHER
    -1.98
    POSITIVE LOGITS
    and
    2.86
    (
    1.95
    ússia
    1.92
     –
    1.80
     Very
    1.72
     aspects
    1.67
    There
    1.66
    which
    1.66
     wußte
    1.66
    AS
    1.65
    Activations Density 0.002%

    No Known Activations