© 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. 22-GEMMASCOPE-RES-131K
    7. 27569
    Prev
    Next
    INDEX
    Explanations

    optical writing type

    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_22/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
     îi
    -1.34
    Endereço
    -1.05
     însă
    -1.02
     schlug
    -0.99
     وقتی
    -0.98
     gekomen
    -0.97
     îl
    -0.97
    isição
    -0.95
     aanges
    -0.94
     dezelfde
    -0.93
    POSITIVE LOGITS
     this
    1.41
     which
    1.40
     where
    1.24
     that
    1.15
     in
    1.12
    ၂
    1.02
     possibly
    0.98
    ၁
    0.97
    QRST
    0.96
    ՝
    0.94
    Activations Density 0.267%

    No Known Activations