© 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. 69832
    Prev
    Next
    INDEX
    Explanations

    questions and decisions

    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
     Instead
    -1.50
     Somewhat
    -1.44
     älteren
    -1.36
     Always
    -1.34
    ganet
    -1.34
     unterstützt
    -1.34
    ◈
    -1.30
    ↵↵↵↵↵↵
    -1.28
     Rather
    -1.27
     Есть
    -1.27
    POSITIVE LOGITS
     you
    2.52
     balans
    1.68
     teolog
    1.53
     kompeti
    1.52
     fön
    1.51
     glatt
    1.48
     seksi
    1.45
    even
    1.45
     rekla
    1.45
     teknis
    1.43
    Activations Density 0.054%

    No Known Activations