© 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. 7-GEMMASCOPE-2-RES-16K
    7. 15021
    Prev
    Next
    INDEX
    Explanations

    try except blocks

    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
    不上
    1.41
    nání
    1.24
    нити
    1.22
    ႏ
    1.21
    たない
    1.20
    হন
    1.19
    không
    1.19
    hopping
    1.18
    tidak
    1.18
    дні
    1.17
    POSITIVE LOGITS
     Δ
    1.47
     Κ
    1.45
     Ла
    1.36
     えっと
    1.35
     Ω
    1.35
     Ά
    1.30
     Mik
    1.30
     פע
    1.28
    参与
    1.27
     Lad
    1.27
    Activations Density 0.214%

    No Known Activations