© 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. 6779
    Prev
    Next
    INDEX
    Explanations

    first ordinal / superlative

    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
     najbol
    0.55
     पसर
    0.54
    まずは
    0.53
    ({},
    0.52
     besten
    0.52
     withheld
    0.51
     delikat
    0.51
    的最佳
    0.50
    ⠄
    0.50
     দেরি
    0.50
    POSITIVE LOGITS
    本格
    0.94
    真正
    0.91
     oficialmente
    0.89
     fully
    0.89
     authenticated
    0.89
     повністю
    0.88
     полноцен
    0.87
     authentically
    0.86
     vollständig
    0.86
     openly
    0.84
    Activations Density 0.261%

    No Known Activations