© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 103794
    Prev
    Next
    INDEX
    Explanations

    module namespace resolution

    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
    imshow
    -0.68
    netti
    -0.67
    jectures
    -0.64
     浪漫
    -0.64
     Франция
    -0.62
    Са
    -0.62
     إد
    -0.61
    寥
    -0.60
    moved
    -0.60
    loger
    -0.60
    POSITIVE LOGITS
    isent
    0.77
    ža
    0.72
     opciones
    0.72
    risation
    0.72
    alta
    0.72
     Gottfried
    0.68
     Mec
    0.67
    ⏸
    0.67
    dels
    0.65
    icin
    0.65
    Activations Density 0.054%

    No Known Activations