© 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. 60516
    Prev
    Next
    INDEX
    Explanations

    Q: identifier:

    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
    gangenen
    -0.97
    otho
    -0.96
     navideña
    -0.87
    ulose
    -0.86
    荘
    -0.85
    cryption
    -0.84
    ützt
    -0.83
    ļas
    -0.82
     hoje
    -0.82
    ценка
    -0.81
    POSITIVE LOGITS
    早期
    0.78
    さき
    0.76
     iyong
    0.68
     Thursday
    0.68
     lentils
    0.68
    貼り
    0.67
     ज्यादा
    0.66
     seperate
    0.66
     grabbing
    0.66
    ิต
    0.66
    Activations Density 0.001%

    No Known Activations