© 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. 63633
    Prev
    Next
    INDEX
    Explanations

    image sources and credits

    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
     emiti
    -0.85
    GEBURTS
    -0.83
    尔
    -0.80
    partie
    -0.76
    粗
    -0.75
    Longrightarrow
    -0.74
    遏
    -0.74
    ohner
    -0.73
     Suddenly
    -0.72
    ':[
    -0.72
    POSITIVE LOGITS
     Unsplash
    1.85
    unsplash
    1.73
     Pixabay
    1.54
     Pexels
    1.48
    Uns
    1.48
    exels
    1.45
    pex
    1.40
    pixabay
    1.35
    Pix
    1.35
     unsplash
    1.30
    Activations Density 0.023%

    No Known Activations