© 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. 77498
    Prev
    Next
    INDEX
    Explanations

    Category and place 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
    onien
    -0.83
    ことなく
    -0.82
     last
    -0.79
     lifetime
    -0.78
    ultimo
    -0.77
    前世
    -0.77
     caminha
    -0.75
     without
    -0.75
    nextNode
    -0.75
    ваете
    -0.74
    POSITIVE LOGITS
    Padding
    0.87
     retras
    0.86
    marginTop
    0.83
     فاصله
    0.81
    Margin
    0.81
     spacer
    0.80
    ്ര
    0.79
    Spacer
    0.78
    margin
    0.78
     Cyr
    0.78
    Activations Density 0.000%

    No Known Activations