© 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. 15447
    Prev
    Next
    INDEX
    Explanations

    to some extent

    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
    大多数
    0.63
    大多數
    0.61
     metade
    0.58
     большинство
    0.54
    ]*
    0.52
    Many
    0.51
    容易
    0.51
    とっても
    0.51
    ](
    0.50
     দেখলেন
    0.50
    POSITIVE LOGITS
     algum
    2.03
     somew
    1.92
     alguma
    1.88
     somehow
    1.82
    某种
    1.77
     algún
    1.72
     some
    1.66
     alguna
    1.65
     Somehow
    1.56
     qualche
    1.55
    Activations Density 0.242%

    No Known Activations