© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77801
    Prev
    Next
    INDEX
    Explanations

    Baroque art and music

    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
    Medieval
    -0.79
     Griffith
    -0.78
     Medieval
    -0.73
    难怪
    -0.73
     Tuch
    -0.72
    esri
    -0.72
    ület
    -0.71
     nồi
    -0.69
     hubo
    -0.69
    頰
    -0.68
    POSITIVE LOGITS
     Baroque
    2.06
     baroque
    1.89
     barro
    1.70
    Bar
    1.35
    BAR
    1.27
     bar
    1.23
    bar
    1.23
     BAR
    1.19
     baro
    1.17
     Bar
    1.06
    Activations Density 0.025%

    No Known Activations