© 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. 7259
    Prev
    Next
    INDEX
    Explanations

    Grant

    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
    ্কর
    1.94
     dotycz
    1.90
     đựng
    1.75
     stocking
    1.74
     nutshell
    1.71
    혔
    1.69
    麽
    1.63
    th
    1.63
     else
    1.61
     Cheer
    1.61
    POSITIVE LOGITS
    ل
    3.06
    在
    2.88
    anın
    2.73
    ور
    2.39
    ার
    2.38
    TE
    2.25
    el
    2.19
    で
    2.16
    ES
    2.14
    لل
    2.14
    Activations Density 0.066%

    No Known Activations