© 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. 101726
    Prev
    Next
    INDEX
    Explanations

    Revolutionary War, ideals, ideas

    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
     The
    -3.09
    wendige
    -2.48
    pecabe
    -2.38
     '
    -2.33
    颳
    -2.31
     \"
    -2.30
     ``
    -2.25
    
    -2.22
    ⬍
    -2.22
    可以选择
    -2.14
    POSITIVE LOGITS
    骓
    2.47
    磲
    2.39
    (?)
    2.33
    沇
    2.33
    縐
    2.28
    𓋼
    2.28
    且
    2.25
    :”
    2.25
    縯
    2.22
    婠
    2.16
    Activations Density 0.002%

    No Known Activations