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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48546
    Prev
    Next
    INDEX
    Explanations

    e-commerce product information

    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
    ýchod
    -0.87
    吖
    -0.86
     emplear
    -0.84
    嘞
    -0.82
     drastically
    -0.82
     and
    -0.80
    하세요
    -0.80
     чудо
    -0.80
     drastic
    -0.79
    呗
    -0.78
    POSITIVE LOGITS
    ）
    0.98
    （
    0.97
     photographed
    0.97
    need
    0.96
     buyers
    0.95
    ｝
    0.95
    getElementsBy
    0.94
     parce
    0.93
     sellers
    0.92
     pictures
    0.91
    Activations Density 0.015%

    No Known Activations