© 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-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 14433
    Prev
    Next
    INDEX
    Explanations

    musician names

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_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
     Prog
    0.60
    prog
    0.59
     Progression
    0.57
     prog
    0.54
     √(
    0.54
     subprocess
    0.53
    Prog
    0.53
    /√
    0.53
     ök
    0.52
     progression
    0.50
    POSITIVE LOGITS
     Mickey
    0.64
    LINK
    0.60
     GARC
    0.59
    DARK
    0.58
    niki
    0.57
     ciento
    0.57
    链接
    0.56
    Garcia
    0.56
     बॉबी
    0.56
    archive
    0.55
    Activations Density 0.006%

    No Known Activations