© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 13247
    Prev
    Next
    INDEX
    Explanations

    people and actions

    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
     Liens
    -1.28
    тила
    -1.19
     permitem
    -1.16
     chèvre
    -1.11
     conseguiu
    -1.10
     forem
    -1.10
     fuis
    -1.09
    粼
    -1.04
     recebeu
    -1.03
     derr
    -1.02
    POSITIVE LOGITS
     four
    1.23
     two
    1.19
     consumer
    1.17
    民眾
    1.16
     five
    1.15
     personally
    1.14
     those
    1.12
     increased
    1.10
     your
    1.07
     близь
    1.07
    Activations Density 0.080%

    No Known Activations