© 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. 19183
    Prev
    Next
    INDEX
    Explanations

    se or si followed by Spanish/Portuguese

    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
     revés
    -2.64
    不明白
    -2.55
    臜
    -2.45
    _
    -2.41
    badan
    -2.39
    穑
    -2.38
    휀
    -2.34
    泱
    -2.33
    sandalia
    -2.30
     caminhada
    -2.30
    POSITIVE LOGITS
    2
    3.02
     \
    2.80
    ‘
    2.34
     viewed
    2.20
     Technically
    2.11
    C
    2.11
    {\
    2.08
    That
    2.02
    玧
    1.98
    <em>
    1.92
    Activations Density 0.001%

    No Known Activations