© 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. 10-GEMMASCOPE-RES-131K
    4. 193
    Prev
    Next
    INDEX
    Explanations

    respected nouns

    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
    ילות
    -2.42
     lidé
    -2.39
     hábiles
    -2.36
     respostas
    -2.34
    ntk
    -2.33
     inept
    -2.22
    דש
    -2.20
     invitar
    -2.19
     sám
    -2.17
     dichas
    -2.13
    POSITIVE LOGITS
     While
    2.69
    (?)
    2.64
    C
    2.61
    E
    2.34
    st
    2.23
    is
    2.23
     jose
    2.22
    Однако
    2.19
     fritt
    2.19
    However
    2.16
    Activations Density 0.004%

    No Known Activations