© 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. 42204
    Prev
    Next
    INDEX
    Explanations

    comparator, TextUtils, or INVALID

    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
    庒
    -2.48
    ,  
    -2.45
    。】
    -2.38
    𖤣
    -2.33
     火鍋
    -2.31
     間取り
    -2.30
    刪除
    -2.30
    ेमाल
    -2.30
     शुर
    -2.22
    ဴ
    -2.22
    POSITIVE LOGITS
     
    3.02
    '
    2.73
    ’
    2.56
    “
    2.42
     et
    2.42
    ate
    2.41
    ?
    2.38
    b
    2.38
     ???
    2.36
     схе
    2.33
    Activations Density 0.000%

    No Known Activations