© 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. 3809
    Prev
    Next
    INDEX
    Explanations

    this is

    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
     or
    -1.59
     other
    -1.46
     all
    -1.43
     兩
    -1.40
     Heute
    -1.37
     員
    -1.35
     裝
    -1.34
    看來
    -1.33
     each
    -1.33
    onacci
    -1.28
    POSITIVE LOGITS
     berpeng
    1.36
    ссии
    1.34
     Rø
    1.30
     вашу
    1.30
     kalau
    1.28
     PopupWindow
    1.26
    ecciones
    1.23
    новен
    1.23
     cocción
    1.23
     efektif
    1.22
    Activations Density 0.058%

    No Known Activations