© 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. 70779
    Prev
    Next
    INDEX
    Explanations

    documentation commands

    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
    '
    -2.16
    沕
    -2.08
     That
    -2.05
     avait
    -2.02
     ancak
    -2.00
     spannende
    -1.95
    llavero
    -1.93
     يمكن
    -1.92
     Then
    -1.91
     важно
    -1.88
    POSITIVE LOGITS
    \
    2.36
     atractiva
    2.33
    ޏ
    2.30
     acoged
    2.19
     \
    2.14
    癪
    2.09
    昞
    2.06
    幪
    2.05
    ✆
    2.03
    嵙
    2.03
    Activations Density 0.003%

    No Known Activations