© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 50897
    Prev
    Next
    INDEX
    Explanations

    Spotify and its contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Measures
    0.43
     сте
    0.43
    провод
    0.40
     Бай
    0.39
     바이
    0.38
    графия
    0.38
    airs
    0.37
    ],"
    0.37
    сте
    0.37
     फिल्में
    0.36
    POSITIVE LOGITS
     Spotify
    0.73
    Spotify
    0.69
     spotify
    0.66
     Wrapped
    0.62
    spotify
    0.54
     wrapped
    0.52
     podcasts
    0.52
     Sweden
    0.51
    Wrapped
    0.51
    wrapped
    0.50
    Activations Density 0.016%

    No Known Activations