© 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. 38667
    Prev
    Next
    INDEX
    Explanations

    domestic social tax subsidy criminal care

    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
     invloed
    -0.90
    pecker
    -0.81
     sobie
    -0.77
     dealing
    -0.74
    finite
    -0.74
    ⎽
    -0.74
    ඔ
    -0.72
     Lein
    -0.71
     Dealing
    -0.71
     kehidupan
    -0.71
    POSITIVE LOGITS
     flexível
    0.75
    僻
    0.73
    André
    0.72
     Morav
    0.71
     emancipation
    0.71
    adamente
    0.71
     Wm
    0.69
     Оно
    0.68
    Trunc
    0.68
     vegetarians
    0.68
    Activations Density 0.028%

    No Known Activations