© 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. 2520
    Prev
    Next
    INDEX
    Explanations

    list iteration and initialization

    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
     款
    1.12
     Autres
    1.09
     ķ
    1.07
     stb
    1.05
     기타
    1.05
    ᄃ
    1.03
    ..)
    1.03
     삶
    1.03
     ন্যায
    1.02
     Etc
    1.01
    POSITIVE LOGITS
    while
    1.35
     while
    1.23
    While
    1.15
     whilst
    1.04
     WHILE
    1.00
     loop
    1.00
     While
    0.97
    loop
    0.95
    Loop
    0.92
     loops
    0.91
    Activations Density 0.014%

    No Known Activations