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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77334
    Prev
    Next
    INDEX
    Explanations

    pink floyd and roger waters

    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
    enterian
    -0.82
     المنتج
    -0.75
     bật
    -0.73
    สนใจ
    -0.72
     træ
    -0.72
    forderung
    -0.71
     freezer
    -0.71
    üğü
    -0.69
    Radi
    -0.69
     Mobility
    -0.69
    POSITIVE LOGITS
     Floyd
    1.21
     Syd
    1.17
     Gilmour
    1.13
    Floyd
    1.09
     Pink
    1.05
     floyd
    0.99
     Roger
    0.96
     Waters
    0.90
    Pink
    0.88
     IOM
    0.85
    Activations Density 0.012%

    No Known Activations