© 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. 119247
    Prev
    Next
    INDEX
    Explanations

    Prior Art, Alex Somian, New Garden, PT cruiser

    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
    仕方ない
    -0.80
     względu
    -0.79
     justifyContent
    -0.78
     entró
    -0.77
     کند
    -0.75
     September
    -0.75
    綢
    -0.75
    четов
    -0.74
     Stär
    -0.74
     rodzaju
    -0.74
    POSITIVE LOGITS
     saying
    1.05
     текста
    0.98
     here
    0.97
     text
    0.97
    setText
    0.96
     says
    0.93
     zegt
    0.91
     Saying
    0.90
    owanie
    0.89
    LTR
    0.89
    Activations Density 0.000%

    No Known Activations