© 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. 13-GEMMASCOPE-2-RES-16K
    7. 2420
    Prev
    Next
    INDEX
    Explanations

    unease and warning

    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_13_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
     ghar
    1.51
    khov
    1.39
     hof
    1.24
    禹
    1.13
     모델
    1.11
     build
    1.09
    Jdk
    1.09
     perfused
    1.08
     bouw
    1.07
    getCurrent
    1.07
    POSITIVE LOGITS
    紙
    2.61
    纸
    2.50
     booklets
    2.42
    印刷
    2.40
     бумаги
    2.30
    printed
    2.29
     Papier
    2.27
     sheets
    2.26
     parchment
    2.24
     carton
    2.23
    Activations Density 1.205%

    No Known Activations