© 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. 32449
    Prev
    Next
    INDEX
    Explanations

    server configuration files

    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
     reflexiones
    -0.85
     konflikt
    -0.83
    ukt
    -0.82
     seba
    -0.82
     personagem
    -0.81
    Seller
    -0.80
    bandcamp
    -0.80
     humanidade
    -0.78
    鸲
    -0.77
    顱
    -0.76
    POSITIVE LOGITS
     best
    0.94
     online
    0.92
     how
    0.90
     Best
    0.86
    وانات
    0.84
    ウェア
    0.82
     Easter
    0.81
     Top
    0.80
    Best
    0.80
     free
    0.78
    Activations Density 0.014%

    No Known Activations