© 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. 9342
    Prev
    Next
    INDEX
    Explanations

    appellate district

    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
     is
    -1.86
    Also
    -1.41
     !
    -1.30
     проблема
    -1.28
     .
    -1.28
     Terkait
    -1.27
    一个是
    -1.26
     wysokość
    -1.26
     a
    -1.24
    otheses
    -1.23
    POSITIVE LOGITS
     ucha
    1.52
     rekla
    1.47
     silikon
    1.46
     kupa
    1.45
     demokra
    1.42
     dekol
    1.41
     of
    1.38
    issão
    1.34
     seksi
    1.34
     hala
    1.34
    Activations Density 0.270%

    No Known Activations