© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47041
    Prev
    Next
    INDEX
    Explanations

    hip-hop music genre

    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
    Negative Logits
    ြ
    -0.81
     protagonista
    -0.77
    ngulo
    -0.74
     ม
    -0.71
     БА
    -0.70
     Bistro
    -0.70
     Crusade
    -0.70
    ネルギー
    -0.68
     HEIGHT
    -0.66
     verknüp
    -0.66
    POSITIVE LOGITS
     hip
    4.63
     Hip
    4.13
    Hip
    3.92
    hip
    3.28
     HIP
    2.84
    HIP
    2.53
     rap
    1.81
     hips
    1.79
     hop
    1.64
     urban
    1.59
    Activations Density 0.052%

    No Known Activations