© 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. 38666
    Prev
    Next
    INDEX
    Explanations

    codes, symbols, and specialized text

    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
     darbu
    -1.08
    🧆
    -1.04
    spricht
    -0.98
    curkan
    -0.97
    Américaine
    -0.90
    şık
    -0.90
     vieta
    -0.90
    gelopen
    -0.90
     darb
    -0.88
    yip
    -0.88
    POSITIVE LOGITS
     these
    1.06
    !
    0.90
    ?
    0.90
    不斷
    0.82
    um
    0.81
    これらの
    0.79
    这些
    0.79
    gin
    0.79
    看书
    0.78
    O
    0.77
    Activations Density 0.005%

    No Known Activations