© 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. 12-GEMMASCOPE-2-RES-16K
    7. 4148
    Prev
    Next
    INDEX
    Explanations

    catch up, catch inconsistencies, catching light

    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_12_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
    ج
    2.33
    لي
    2.20
     불구
    2.13
    رف
    2.08
    那我
    1.95
    א
    1.95
    গ
    1.94
    اب
    1.93
     mangiare
    1.91
     exfol
    1.91
    POSITIVE LOGITS
     Section
    1.67
     Catch
    1.62
     glimpse
    1.61
    dwelling
    1.51
     buil
    1.48
    くらいの
    1.45
    toluene
    1.44
    de
    1.43
    য়াদ
    1.43
    ━━
    1.39
    Activations Density 0.204%

    No Known Activations