© 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. 22-GEMMASCOPE-RES-131K
    7. 28643
    Prev
    Next
    INDEX
    Explanations

    Components and Forms

    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_22/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
     attiv
    -1.28
     日常
    -1.25
     the
    -1.24
    ;”
    -1.21
     بشه
    -1.20
    ”;
    -1.20
    '];
    -1.20
    😓
    -1.19
    のお知らせ
    -1.16
    ')";
    -1.15
    POSITIVE LOGITS
    了一个
    1.31
                    
    1.25
    платье
    1.23
     árvore
    1.19
    她们
    1.11
     fazia
    1.11
     dizem
    1.09
     estadía
    1.09
    などが
    1.07
    人气
    1.06
    Activations Density 0.006%

    No Known Activations