© 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. 1305
    Prev
    Next
    INDEX
    Explanations

    music and entertainment figures

    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
    𝕨
    -0.81
    ịnh
    -0.80
    annon
    -0.76
     vr
    -0.74
     bere
    -0.74
    ullen
    -0.73
    品牌的
    -0.73
     Hyperion
    -0.72
     Holden
    -0.72
    采集
    -0.72
    POSITIVE LOGITS
     Ghanaian
    1.03
     rapper
    1.02
     DJ
    1.02
     Davido
    0.99
     Wiz
    0.94
    ]}{
    0.90
     artists
    0.87
     singer
    0.87
    Wiz
    0.85
     actress
    0.85
    Activations Density 0.012%

    No Known Activations