© 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. 31615
    Prev
    Next
    INDEX
    Explanations

    Dean, Journalism, Media, Public Editor

    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
    itchfield
    -0.82
     Tensile
    -0.72
    рист
    -0.71
    elseif
    -0.71
    pgsql
    -0.70
     hist
    -0.70
    dellin
    -0.69
    plotlib
    -0.68
    totalPages
    -0.68
     antigen
    -0.67
    POSITIVE LOGITS
     Media
    2.27
    Media
    2.08
     media
    1.92
     Journalism
    1.80
     Communication
    1.68
     MEDIA
    1.68
    media
    1.66
     journalism
    1.62
    MEDIA
    1.55
    Communication
    1.52
    Activations Density 0.061%

    No Known Activations