© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 2369
    Prev
    Next
    INDEX
    Explanations

    code `en` and `best` with hyphens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
    参
    0.63
    শিপ
    0.62
    ური
    0.60
    fore
    0.58
    ネ
    0.58
     গঠ
    0.57
    पदा
    0.57
    ideal
    0.56
    苹
    0.56
    วม
    0.56
    POSITIVE LOGITS
    ‐
    1.78
    ‑
    1.68
    -​
    1.58
    ־
    1.38
    
    1.35
    ﹣
    1.28
    \-
    1.06
    ⁃
    1.06
    ‒
    1.04
    
    1.00
    Activations Density 0.816%

    No Known Activations