© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 84409
    Prev
    Next
    INDEX
    Explanations

    #include or fill_in

    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
     smar
    -0.69
    read
    -0.66
    eleste
    -0.65
     tiegħek
    -0.63
    コンセプト
    -0.63
     Shortly
    -0.63
    colta
    -0.63
     read
    -0.62
     rolo
    -0.62
    طفال
    -0.62
    POSITIVE LOGITS
    squad
    0.75
    rook
    0.74
     ook
    0.72
     Productos
    0.69
     Oy
    0.68
     schreef
    0.68
    zhen
    0.66
     fallas
    0.66
     calles
    0.66
    Rourke
    0.65
    Activations Density 0.127%

    No Known Activations