© 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. 97
    Prev
    Next
    INDEX
    Explanations

    elongated sounds and exclamations

    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
     {
    -2.45
    -2.39
    H
    -2.23
     `
    -2.23
     you
    -2.23
     puis
    -2.17
    ኧ
    -2.16
    w
    -2.11
    X
    -2.09
    at
    -2.08
    POSITIVE LOGITS
    蟶
    2.45
    時尚
    2.23
     étaient
    2.16
     goederen
    2.16
     entsprechende
    2.13
     traditionelle
    2.11
     afbeeldingen
    2.09
    :✨
    2.08
    You
    2.08
     étoient
    2.06
    Activations Density 0.014%

    No Known Activations