© 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. 107980
    Prev
    Next
    INDEX
    Explanations

    .html

    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
     aast
    -0.78
    الة
    -0.76
    Flere
    -0.75
     Angeli
    -0.73
    【
    -0.72
    López
    -0.71
    costal
    -0.70
     shutil
    -0.69
     fotos
    -0.69
    形容
    -0.69
    POSITIVE LOGITS
    COOK
    0.79
     tài
    0.78
     DEA
    0.77
     colecciones
    0.76
    parian
    0.75
     malic
    0.73
     Tài
    0.73
    Ryo
    0.73
    RUnlock
    0.73
     tätig
    0.73
    Activations Density 0.020%

    No Known Activations