© 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. 22-GEMMASCOPE-RES-131K
    7. 28115
    Prev
    Next
    INDEX
    Explanations

    EPI readout, USS ships, stock market news

    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
     it
    -1.41
     Commentaires
    -1.24
    ってしまった
    -1.22
     I
    -1.17
    bouts
    -1.13
     bolso
    -1.13
     naast
    -1.09
     colchón
    -1.09
     masculino
    -1.08
     balcón
    -1.07
    POSITIVE LOGITS
    توضیحات
    1.55
     foglie
    1.43
    معرفی
    1.40
     ร์
    1.39
    Actually
    1.30
    vantaged
    1.30
    Angebot
    1.30
    pierw
    1.27
    Hersteller
    1.27
    Vrij
    1.27
    Activations Density 0.003%

    No Known Activations