© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 17-GEMMASCOPE-2-RES-16K
    7. 596
    Prev
    Next
    INDEX
    Explanations

    Western scale

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_17_width_16k_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
    Proxy
    1.15
    proxy
    1.09
     SWOT
    1.04
     REIT
    1.03
    蛭
    0.98
     Shareholders
    0.98
     FDI
    0.97
    ⿸
    0.96
     PFAS
    0.95
    物流
    0.95
    POSITIVE LOGITS
     music
    4.36
     musicians
    4.18
     musik
    4.17
     musical
    4.16
     Music
    4.11
     음악
    4.10
     songs
    4.05
    音乐
    4.04
     música
    4.03
     musique
    4.01
    Activations Density 3.118%

    No Known Activations