© 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. 34-GEMMASCOPE-RES-131K
    7. 91096
    Prev
    Next
    INDEX
    Explanations

    figuring out

    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_34/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
     professores
    -0.96
     penser
    -0.95
    ότητα
    -0.94
     هنا
    -0.94
    Grup
    -0.94
    Inne
    -0.93
     معلومات
    -0.91
    フラー
    -0.89
     Grup
    -0.89
    Suk
    -0.88
    POSITIVE LOGITS
     out
    1.77
     how
    1.66
     what
    1.57
     where
    1.52
     figured
    1.23
    what
    1.18
     this
    1.17
     figuring
    1.11
     if
    1.09
     it
    1.09
    Activations Density 0.017%

    No Known Activations