© 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. 65345
    Prev
    Next
    INDEX
    Explanations

    assert and query usage

    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
     "
    -1.79
     for
    -1.51
     planète
    -1.50
     from
    -1.45
    ⃨
    -1.39
     hinder
    -1.36
     языка
    -1.36
    Viewing
    -1.31
     directamente
    -1.30
     веке
    -1.29
    POSITIVE LOGITS
     радо
    1.45
     reaffirm
    1.35
    🩲
    1.34
    enablog
    1.32
     abode
    1.31
    estão
    1.30
     экономи
    1.30
    ()
    1.29
     dieß
    1.29
    \">
    1.28
    Activations Density 0.006%

    No Known Activations