© 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. 41980
    Prev
    Next
    INDEX
    Explanations

    describes states or 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_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
    Publié
    -1.45
    Beaucoup
    -1.36
     você
    -1.36
     DOMINGO
    -1.26
     всю
    -1.26
    ってみて
    -1.26
    foreignKey
    -1.24
     beginnen
    -1.24
    Приготовление
    -1.24
     you
    -1.23
    POSITIVE LOGITS
     its
    1.73
     S
    1.40
    และ
    1.29
     R
    1.25
     M
    1.24
     चीज़
    1.23
     jenem
    1.23
     and
    1.22
    自己的
    1.21
     irgende
    1.19
    Activations Density 0.281%

    No Known Activations