© 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. 70038
    Prev
    Next
    INDEX
    Explanations

    pop music singers and stars

    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
    akka
    -0.89
    specialchars
    -0.82
    actor
    -0.81
     actors
    -0.78
    创业
    -0.78
    tispiece
    -0.77
    Actors
    -0.77
     for
    -0.77
    Startup
    -0.76
     Actors
    -0.76
    POSITIVE LOGITS
     Grammy
    1.58
     Billboard
    1.54
     music
    1.53
     singer
    1.47
     songs
    1.42
     singers
    1.41
     Gramm
    1.35
     album
    1.34
    Billboard
    1.32
     pop
    1.30
    Activations Density 0.093%

    No Known Activations