© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 98756
    Prev
    Next
    INDEX
    Explanations

    government officials and legal proceedings

    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
    CHARS
    -0.86
     edema
    -0.79
    lsp
    -0.79
    ölcs
    -0.79
     científico
    -0.78
    alties
    -0.77
     }}^{
    -0.77
     à
    -0.74
    ຄ
    -0.74
     rainbow
    -0.73
    POSITIVE LOGITS
    opin
    0.72
    fatti
    0.71
    先輩
    0.68
     cartera
    0.67
    katakan
    0.66
    ffes
    0.66
     কর
    0.65
    informat
    0.64
     diputados
    0.64
     policymakers
    0.64
    Activations Density 0.023%

    No Known Activations