© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77994
    Prev
    Next
    INDEX
    Explanations

    featured artists and guests

    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
    Music
    -0.85
     concerts
    -0.80
     Music
    -0.79
    ık
    -0.79
     музыку
    -0.75
    Components
    -0.75
     Música
    -0.74
     explica
    -0.73
     musicale
    -0.73
    getDriver
    -0.73
    POSITIVE LOGITS
     guest
    2.36
     featured
    1.96
    guest
    1.86
     collaboration
    1.85
     collaborations
    1.77
     feature
    1.74
     features
    1.72
    Guest
    1.65
     Guest
    1.63
    collaboration
    1.63
    Activations Density 0.033%

    No Known Activations