© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 81157
    Prev
    Next
    INDEX
    Explanations

    declaration of a class

    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
    rises
    -0.74
    federal
    -0.73
     السف
    -0.72
     Kamen
    -0.71
    ّم
    -0.71
     federal
    -0.69
     spela
    -0.68
    켈
    -0.67
     rospy
    -0.67
     Kelurahan
    -0.67
    POSITIVE LOGITS
     cytometry
    0.86
    gridColumn
    0.77
    ndag
    0.77
    ⟬
    0.76
    购
    0.75
     rộng
    0.73
     stalwart
    0.72
     Bon
    0.71
     firmament
    0.71
     abject
    0.71
    Activations Density 0.000%

    No Known Activations