© 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-262K
    7. 34465
    Prev
    Next
    INDEX
    Explanations

    sulfuric acid

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    l
    1.73
    습니다
    1.65
    이에
    1.65
    𝘋
    1.61
    ين
    1.60
    є
    1.60
    ен
    1.59
    n
    1.59
    𝙸
    1.55
    મે
    1.53
    POSITIVE LOGITS
    cción
    2.13
    zame
    2.05
     характера
    1.96
    nosti
    1.95
    nment
    1.94
    ございました
    1.93
    punten
    1.93
    ziele
    1.91
    hlas
    1.91
     dàng
    1.90
    Activations Density 0.006%

    No Known Activations