© 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. 90355
    Prev
    Next
    INDEX
    Explanations

    between phrases and ranges

    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
     taxe
    -0.87
    服用
    -0.85
    ーー
    -0.85
    𓐍
    -0.85
    谆
    -0.85
    unuz
    -0.83
     Ziegler
    -0.82
    lllllll
    -0.82
    手術
    -0.81
    nikova
    -0.80
    POSITIVE LOGITS
     them
    1.60
     themselves
    1.19
     autres
    1.04
     осуществляется
    1.01
     mantiene
    0.99
     desarrolla
    0.93
    ことで
    0.91
     otras
    0.90
     ellos
    0.90
     них
    0.90
    Activations Density 0.029%

    No Known Activations