© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15038
    Prev
    Next
    INDEX
    Explanations

    more... better

    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
     nieco
    0.59
    ouncing
    0.57
     Somewhat
    0.56
     asegur
    0.55
     somewhat
    0.52
     చూడ
    0.52
    懶
    0.52
     suivi
    0.51
    也很
    0.50
     memastikan
    0.50
    POSITIVE LOGITS
     càng
    1.53
    越多
    1.49
    越大
    1.34
    越高
    1.28
    越
    1.27
     desto
    1.20
     जितना
    1.20
     semakin
    1.13
     যত
    1.09
    ยิ่ง
    1.07
    Activations Density 0.181%

    No Known Activations