© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1368
    Prev
    Next
    INDEX
    Explanations

    concessive clauses

    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
    หรือ
    1.15
    และ
    1.09
    或
    1.09
    ที่เป็น
    1.08
    및
    1.06
    が一
    1.04
    和一个
    1.03
    和
    1.01
     или
    1.01
    và
    0.99
    POSITIVE LOGITS
     although
    2.42
     despite
    2.04
    although
    1.91
     while
    1.91
     whilst
    1.91
     unless
    1.85
     meskipun
    1.83
    despite
    1.80
     whereas
    1.76
     pokud
    1.75
    Activations Density 0.391%

    No Known Activations