© 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. 47792
    Prev
    Next
    INDEX
    Explanations

    ship class names

    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
     AUSSI
    -0.82
     tendrán
    -0.69
    感受
    -0.69
     thermos
    -0.69
    Ease
    -0.67
     Sambo
    -0.66
    Dedu
    -0.66
    ײ
    -0.66
     ارسال
    -0.66
    agnos
    -0.66
    POSITIVE LOGITS
     class
    2.11
    class
    1.67
     Class
    1.66
     classe
    1.56
    Class
    1.34
     classes
    1.34
     clase
    1.30
     kelas
    1.27
    classe
    1.18
     CLASS
    1.16
    Activations Density 0.038%

    No Known Activations