© 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. 20490
    Prev
    Next
    INDEX
    Explanations

    hoped for outcomes

    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
     divertidas
    -2.78
     ramas
    -2.47
     marea
    -2.44
     motivadoras
    -2.42
    وضح
    -2.39
    ſelves
    -2.36
    ⃙
    -2.33
    ⼥
    -2.28
     pomen
    -2.27
    ၄
    -2.27
    POSITIVE LOGITS
    "
    4.72
    '
    3.88
    of
    3.67
    4
    3.33
    5
    2.92
    饪
    2.73
    [
    2.73
    si
    2.67
    1
    2.66
    ?
    2.50
    Activations Density 0.003%

    No Known Activations