© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 10536
    Prev
    Next
    INDEX
    Explanations

    trying to capture

    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
    Negative Logits
    s
    2.31
    b
    1.99
    n
    1.94
    så
    1.92
    it
    1.91
    یت
    1.88
    ди
    1.87
    p
    1.84
    ship
    1.82
    го
    1.74
    POSITIVE LOGITS
    芏
    2.11
    あります
    1.91
    😍😍
    1.90
    即便
    1.80
    ার
    1.73
    다
    1.71
    ありますが
    1.70
     américain
    1.67
    锼
    1.66
    JOHN
    1.65
    Activations Density 0.038%

    No Known Activations