© 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. 38027
    Prev
    Next
    INDEX
    Explanations

    item; activity; sample

    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
     эффек
    -0.65
    ôt
    -0.65
     hash
    -0.65
    pik
    -0.65
     разработ
    -0.64
     Miracles
    -0.63
     vok
    -0.63
     Isabel
    -0.63
     miracle
    -0.63
    ೀ
    -0.62
    POSITIVE LOGITS
    odios
    0.79
    璐
    0.76
    scipy
    0.70
    ριά
    0.69
     phố
    0.69
    ışık
    0.68
     modifications
    0.68
    岁的
    0.67
     deodorant
    0.67
     deregulation
    0.66
    Activations Density 0.065%

    No Known Activations