© 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-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6694
    Prev
    Next
    INDEX
    Explanations

    contrasting conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,
    0.86
    ،
    0.60
     कों
    0.57
    ඬ
    0.56
     yac
    0.55
     Deane
    0.55
    gı
    0.55
     tide
    0.54
     soms
    0.54
     multer
    0.54
    POSITIVE LOGITS
     obwohl
    0.86
    ／
    0.72
    었고
    0.66
    欴
    0.63
     exactamente
    0.61
    และ
    0.60
    porque
    0.60
     (
    0.59
    because
    0.57
    いましたが
    0.57
    Activations Density 0.038%

    No Known Activations