© 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. 3541
    Prev
    Next
    INDEX
    Explanations

    slice of

    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
     yks
    0.60
     刺繍
    0.57
     pemerintah
    0.52
    ပေါင်း
    0.52
     government
    0.51
     nascost
    0.51
    ӧ
    0.51
     ڈپ
    0.50
     विषा
    0.50
     Tü
    0.50
    POSITIVE LOGITS
     cut
    2.44
     cuts
    2.33
     cutting
    2.28
    Cut
    2.23
    Cutting
    2.19
     Cut
    2.13
     cắt
    2.09
     CUT
    2.08
    切割
    2.08
    cut
    2.06
    Activations Density 0.433%

    No Known Activations