© 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. 9976
    Prev
    Next
    INDEX
    Explanations

    Leader, quantitative, social

    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
     також
    -1.44
     Also
    -1.32
     also
    -1.31
     również
    -1.27
     tiež
    -1.21
     fören
    -1.21
    和歌
    -1.17
     myös
    -1.16
    اریخ
    -1.15
    了出来
    -1.15
    POSITIVE LOGITS
     of
    1.55
    still
    1.32
     a
    1.28
    .
    1.27
     such
    1.23
    ,
    1.12
     masih
    1.05
     ancora
    1.03
     success
    1.00
     CONTEST
    0.99
    Activations Density 0.221%

    No Known Activations