© 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
    2. Gemma-3-12B
    3. 41-GEMMASCOPE-2-RES-65K
    4. 15593
    Prev
    Next
    INDEX
    Explanations

    famous people/works

    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
     Dried
    0.59
     FV
    0.53
    笺
    0.51
     Seed
    0.50
     মোর
    0.50
    Dried
    0.50
     CEM
    0.50
     Forward
    0.48
    
    0.48
     দ্বিত
    0.48
    POSITIVE LOGITS
     Beatles
    2.03
     Beethoven
    2.03
    Shakespeare
    1.96
     Shakespeare
    1.95
     Mozart
    1.91
     Beyonce
    1.88
     shakespeare
    1.79
     Kubrick
    1.77
     Oprah
    1.77
     Beyoncé
    1.72
    Activations Density 0.084%

    No Known Activations