© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2876
    Prev
    Next
    INDEX
    Explanations

    person speaking or quoted

    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
     writing
    -1.23
     written
    -0.99
     Writing
    -0.91
     tulisan
    -0.90
    writing
    -0.88
    Writing
    -0.87
     posting
    -0.85
     write
    -0.85
     schreiben
    -0.82
     skriva
    -0.82
    POSITIVE LOGITS
     начал
    1.15
     شروع
    1.02
     comienza
    1.01
     begins
    1.01
     comenzó
    1.00
    开始
    0.99
     начала
    0.99
     mówi
    0.96
     BEGIN
    0.96
     firstly
    0.96
    Activations Density 0.011%

    No Known Activations