© 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. 104533
    Prev
    Next
    INDEX
    Explanations

    think tanks and academic institutions

    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
    蓐
    -1.47
     instruk
    -1.41
    unten
    -1.41
     Escrit
    -1.39
     Contribu
    -1.38
    Цели
    -1.37
     lokalen
    -1.37
    Цитата
    -1.35
    啵
    -1.33
    淠
    -1.32
    POSITIVE LOGITS
    mathrm
    1.47
     then
    1.38
    ?”,
    1.26
     vienas
    1.22
     what
    1.18
    \
    1.16
    Sedangkan
    1.13
     want
    1.12
    Datas
    1.11
     cupola
    1.08
    Activations Density 0.082%

    No Known Activations