© 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. 75926
    Prev
    Next
    INDEX
    Explanations

    drum and drum-related concepts

    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
    くれる
    -0.91
     Unterschiede
    -0.89
     somewhat
    -0.86
    seamnă
    -0.85
    
    -0.81
     dueño
    -0.80
     streamed
    -0.79
     гораздо
    -0.78
     Somewhat
    -0.77
    similar
    -0.77
    POSITIVE LOGITS
    drum
    1.29
    mers
    1.24
     Drum
    1.16
    Drum
    1.09
     DRUM
    1.05
    🥁
    1.04
     Drummond
    1.00
     drum
    0.98
    ocyto
    0.91
    tembre
    0.88
    Activations Density 0.012%

    No Known Activations