© 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. 9793
    Prev
    Next
    INDEX
    Explanations

    produce variations

    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
    橚
    -2.36
     pérd
    -2.19
    釓
    -2.17
     they
    -2.09
    岨
    -1.93
    𓋼
    -1.90
     cinque
    -1.84
    être
    -1.80
    事は
    -1.79
    eight
    -1.78
    POSITIVE LOGITS
     What
    2.00
    {
    1.84
     an
    1.79
     Some
    1.75
     Maybe
    1.66
     There
    1.65
     廠
    1.62
     Usually
    1.57
     If
    1.55
     Probably
    1.55
    Activations Density 0.057%

    No Known Activations