© 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. 123931
    Prev
    Next
    INDEX
    Explanations

    Names followed by descriptions or classifications

    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
    {~
    -1.56
    providedIn
    -1.55
    圌
    -1.50
     your
    -1.48
    骉
    -1.39
    蓠
    -1.37
    >=</
    -1.36
    ين
    -1.36
    ⫹
    -1.34
    に似
    -1.32
    POSITIVE LOGITS
     for
    1.58
    荩
    1.38
     while
    1.38
     because
    1.38
    也就
    1.32
     aasta
    1.30
    s
    1.29
     keben
    1.27
     didn
    1.27
     even
    1.27
    Activations Density 0.116%

    No Known Activations