© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 6255
    Prev
    Next
    INDEX
    Explanations

    musicians and bands

    np_acts-logits-general · gemini-2.5-flash-lite

    musicians after "by"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pradesh
    0.46
     itemList
    0.44
     регуляр
    0.43
     upstream
    0.40
     alen
    0.40
     centralized
    0.40
     Contribution
    0.40
    陂
    0.39
     clonal
    0.39
    فعيل
    0.39
    POSITIVE LOGITS
     Coldplay
    1.74
     Eminem
    1.66
     Metallica
    1.62
     Beyonce
    1.44
     Beyoncé
    1.41
     Beatles
    1.33
     Kanye
    1.29
     Britney
    1.27
     Rihanna
    1.26
     Springsteen
    1.26
    Activations Density 0.209%

    No Known Activations