© 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. 110704
    Prev
    Next
    INDEX
    Explanations

    rights reserved

    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
    wavelength
    -0.75
    [{\
    -0.66
    citep
    -0.65
     lavish
    -0.65
    blocking
    -0.64
    لوم
    -0.64
     acrylic
    -0.64
    ولت
    -0.63
    橋本
    -0.63
    حديث
    -0.62
    POSITIVE LOGITS
    ows
    0.70
     MediaQuery
    0.68
    cador
    0.68
    bau
    0.68
     ای
    0.68
     شاهد
    0.67
    mensaje
    0.67
    Пи
    0.66
    BIG
    0.66
     način
    0.65
    Activations Density 0.081%

    No Known Activations