© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 12946
    Prev
    Next
    INDEX
    Explanations

    names following by context

    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
     They
    -2.77
    我先
    -2.52
    晅
    -2.50
    ︲
    -2.48
    を作って
    -2.47
    两天
    -2.38
    a
    -2.38
    閦
    -2.34
    我把
    -2.34
     illustrate
    -2.34
    POSITIVE LOGITS
     are
    2.58
    嚙
    2.48
     adventures
    2.47
     extérieurs
    2.41
     orari
    2.39
     botol
    2.36
     menyen
    2.34
     diki
    2.33
     hırka
    2.33
     問
    2.31
    Activations Density 0.857%

    No Known Activations