© 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. 78018
    Prev
    Next
    INDEX
    Explanations

    Date Filed

    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
    iral
    -0.74
    졌
    -0.68
    header
    -0.68
     Stavanger
    -0.68
    Head
    -0.67
     comprendre
    -0.67
    头
    -0.66
     труб
    -0.66
     desplazamiento
    -0.66
     Spreadsheet
    -0.65
    POSITIVE LOGITS
    retim
    0.78
     limita
    0.70
    ophenol
    0.70
    hez
    0.67
     moda
    0.66
     politica
    0.66
     deco
    0.66
    ysuckle
    0.66
    eline
    0.65
     paja
    0.65
    Activations Density 0.050%

    No Known Activations