© 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. 108080
    Prev
    Next
    INDEX
    Explanations

    court district division

    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
    ITERATURE
    -0.71
     improvement
    -0.67
     Improved
    -0.67
     improved
    -0.67
    BagConstraints
    -0.67
    щество
    -0.66
     reivindic
    -0.66
    ué
    -0.65
    cionado
    -0.65
     improvements
    -0.64
    POSITIVE LOGITS
     grunn
    0.71
     creo
    0.69
    êtement
    0.68
    Ǎ
    0.67
     foal
    0.67
     gewoon
    0.66
     tots
    0.66
     '\''
    0.65
     يل
    0.65
    rätt
    0.65
    Activations Density 0.066%

    No Known Activations