© 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. 127361
    Prev
    Next
    INDEX
    Explanations

    code comments and line breaks

    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
    HomeComponent
    -1.48
     Gonna
    -1.48
     Furcht
    -1.45
    和
    -1.44
    居然
    -1.41
    🢒
    -1.40
     என்று
    -1.38
     pentru
    -1.37
     dagli
    -1.34
    estrian
    -1.30
    POSITIVE LOGITS
    鹟
    1.55
     minimalista
    1.55
     sólido
    1.54
     Reſ
    1.48
    不喜欢
    1.45
    酹
    1.45
     paſſ
    1.43
     parecido
    1.42
     tatou
    1.42
    ことはありません
    1.39
    Activations Density 0.001%

    No Known Activations