© 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. 98705
    Prev
    Next
    INDEX
    Explanations

    hip hop

    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
     —
    -0.74
     Whe
    -0.71
     espécies
    -0.70
     of
    -0.69
     
    -0.68
    ẩu
    -0.68
    階段
    -0.68
     meisten
    -0.67
    holes
    -0.66
    ver
    -0.65
    POSITIVE LOGITS
     Hip
    1.77
     hip
    1.73
     hop
    1.67
    Hip
    1.52
     Hop
    1.43
    HOP
    1.31
     HIP
    1.30
    hop
    1.29
    Hop
    1.29
     HOP
    1.19
    Activations Density 0.013%

    No Known Activations