© 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-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 1014
    Prev
    Next
    INDEX
    Explanations

    running code or simulations

    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_7_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
    thiophen
    2.69
     боя
    2.50
    ở
    2.46
    꽂
    2.45
     porté
    2.45
    NOWLEDG
    2.41
     trộn
    2.39
     definición
    2.38
    κολ
    2.37
    舒適
    2.36
    POSITIVE LOGITS
     NPM
    2.60
     HAT
    2.50
    োগ্য
    2.45
    riages
    2.45
     WARRANTY
    2.43
    秅
    2.40
    nen
    2.35
    OnUiThread
    2.34
    ngo
    2.33
    চলে
    2.33
    Activations Density 0.451%

    No Known Activations