© 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. 34-GEMMASCOPE-RES-131K
    7. 77227
    Prev
    Next
    INDEX
    Explanations

    information regarding license

    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
    model
    -0.69
    Diagram
    -0.67
    ategory
    -0.67
    Posts
    -0.65
     Laing
    -0.65
    𝑁
    -0.65
    llas
    -0.64
    ünster
    -0.63
    팀
    -0.63
     Diagram
    -0.63
    POSITIVE LOGITS
     lú
    0.78
    Vish
    0.76
    Sea
    0.71
     Sea
    0.71
    ebly
    0.69
     inefficient
    0.69
    Slovakia
    0.69
    reducible
    0.69
     cies
    0.67
    LEGEND
    0.67
    Activations Density 0.041%

    No Known Activations