© 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. 42583
    Prev
    Next
    INDEX
    Explanations

    arguing, claiming, explaining, justifying

    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
    不同
    -1.50
     different
    -1.46
    <b>
    -1.44
     <
    -1.41
     they
    -1.36
    <
    -1.31
    class
    -1.30
    request
    -1.30
    i
    -1.30
    nt
    -1.27
    POSITIVE LOGITS
     indescri
    1.41
    nė
    1.39
     unspeak
    1.39
     pears
    1.36
     comenzará
    1.34
    Sudah
    1.31
     brevemente
    1.30
    谙
    1.30
    upné
    1.30
    FOTOS
    1.30
    Activations Density 0.078%

    No Known Activations