© 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. 87045
    Prev
    Next
    INDEX
    Explanations

    persist

    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
    蟥
    -3.17
    拊
    -2.73
    氿
    -2.59
    翃
    -2.58
    ꔹ
    -2.42
     ´
    -2.38
     trajes
    -2.31
    溦
    -2.25
    GEBUR
    -2.23
    ౮
    -2.23
    POSITIVE LOGITS
    應該
    2.17
     Not
    2.17
    \
    2.17
    ;
    2.14
     at
    2.09
    n
    2.05
     Она
    1.93
     यदि
    1.91
     Despite
    1.89
    已经
    1.87
    Activations Density 0.011%

    No Known Activations