© 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-3-1B
    5. 17-GEMMASCOPE-2-RES-16K
    7. 2249
    Prev
    Next
    INDEX
    Explanations

    regulations and codes

    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
    􀂃
    1.11
    
    1.09
    Integer
    0.94
    osex
    0.93
    􀂾
    0.90
     Gujar
    0.88
    Sept
    0.88
    Bombay
    0.87
     Integer
    0.87
    νοι
    0.86
    POSITIVE LOGITS
     Figma
    1.55
     tiktok
    1.54
     npm
    1.46
     useEffect
    1.44
    vercel
    1.44
     webpack
    1.42
     setInterval
    1.35
     TikTok
    1.35
    🤏
    1.29
     Axios
    1.28
    Activations Density 0.001%

    No Known Activations