© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1706
    Prev
    Next
    INDEX
    Explanations

    jade garden or jade car

    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
     Loss
    -0.79
     erfolgreiche
    -0.78
    restrial
    -0.77
     Companies
    -0.76
     Wayne
    -0.75
     Hampshire
    -0.75
    nerie
    -0.75
    万物
    -0.74
    PARATUS
    -0.74
    rétaire
    -0.73
    POSITIVE LOGITS
     signify
    0.81
     getModel
    0.77
     attaques
    0.75
     engendered
    0.73
    😡
    0.71
    Jade
    0.71
     envo
    0.70
    these
    0.70
     getIs
    0.70
    tte
    0.70
    Activations Density 0.011%

    No Known Activations