© 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. 63775
    Prev
    Next
    INDEX
    Explanations

    dimensions x and by

    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
    年には
    -0.93
    <i>
    -0.93
     conjunta
    -0.91
    などが
    -0.90
    全ての
    -0.87
     十
    -0.87
     that
    -0.85
    <b>
    -0.85
    转型
    -0.83
    呦
    -0.83
    POSITIVE LOGITS
    ',
    1.02
    woners
    0.93
    printLine
    0.90
     Bha
    0.90
    
    0.90
    ποι
    0.89
     révélé
    0.88
    splitContainer
    0.88
    Arbe
    0.86
    ᴼ
    0.84
    Activations Density 0.029%

    No Known Activations