© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 42787
    Prev
    Next
    INDEX
    Explanations

    kids and family activities

    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
     as
    -1.46
    k
    -1.41
    $
    -1.28
    ↵
    -1.27
     свою
    -1.22
    ).
    -1.20
    inch
    -1.18
    s
    -1.16
    <em>
    -1.14
     CONTRA
    -1.13
    POSITIVE LOGITS
     apoi
    1.62
     then
    1.59
    ꜄
    1.42
     řízení
    1.38
    
    1.34
    occuper
    1.33
     trám
    1.32
     šť
    1.29
     имеют
    1.29
     alguns
    1.28
    Activations Density 0.030%

    No Known Activations