© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8118
    Prev
    Next
    INDEX
    Explanations

    despite

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_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
    まず
    0.76
    まずは
    0.66
    depends
    0.61
     まず
    0.61
     firstly
    0.60
    엮
    0.59
    首先
    0.57
    とりあえず
    0.57
     首先
    0.57
    });
    0.56
    POSITIVE LOGITS
     pourtant
    1.29
     malgré
    1.27
     Malgré
    1.26
     despite
    1.23
     Despite
    1.21
     warnings
    1.13
    Despite
    1.12
     rağmen
    1.06
    despite
    1.06
     apesar
    1.03
    Activations Density 0.221%

    No Known Activations