© 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. 86799
    Prev
    Next
    INDEX
    Explanations

    CreateObject, GetObject, scripting

    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
    찰
    -0.84
    Leistung
    -0.80
     Contracts
    -0.77
     Contract
    -0.74
     nine
    -0.72
     Haftung
    -0.71
    tki
    -0.71
     economic
    -0.70
     contracts
    -0.70
     eight
    -0.69
    POSITIVE LOGITS
    Scripting
    0.87
    documentclass
    0.84
    UnitTesting
    0.78
     Dominion
    0.77
    versario
    0.75
    MCA
    0.72
    ennio
    0.71
    azol
    0.70
     obj
    0.70
     Tân
    0.69
    Activations Density 0.070%

    No Known Activations