© 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. 4209
    Prev
    Next
    INDEX
    Explanations

    details or specific labels

    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
     tarik
    -0.80
    Iranian
    -0.78
     Iranian
    -0.77
    alisa
    -0.74
     espiritual
    -0.73
    likte
    -0.73
     biological
    -0.72
     bré
    -0.72
     ?...
    -0.72
     kela
    -0.71
    POSITIVE LOGITS
    enqueue
    0.91
     OLS
    0.90
    FAIL
    0.85
    ępnie
    0.85
     medalist
    0.85
    PCell
    0.85
     detalhes
    0.84
    DETAILS
    0.83
    details
    0.81
    跶
    0.81
    Activations Density 0.001%

    No Known Activations