© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 6752
    Prev
    Next
    INDEX
    Explanations

    defining terms in agreements

    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
     коронави
    1.18
    蔡
    1.11
    emort
    1.09
    ⊂
    1.08
     秒
    1.03
     সিঁ
    1.02
     смартфо
    1.02
    咬
    1.02
    Covid
    1.02
    怼
    1.00
    POSITIVE LOGITS
     tutto
    1.04
     rg
    0.98
     ve
    0.97
     mett
    0.94
     newest
    0.93
     majesty
    0.93
     extremity
    0.90
     tudo
    0.90
     reich
    0.89
     Lassen
    0.89
    Activations Density 0.038%

    No Known Activations