© 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. 10641
    Prev
    Next
    INDEX
    Explanations

    structure and forward

    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
     μέσω
    1.02
    ﻥ
    0.88
     Wetlands
    0.87
     önemlidir
    0.86
     Demographic
    0.84
    の大
    0.84
     Während
    0.83
    უნქ
    0.83
     қ
    0.82
     Однако
    0.81
    POSITIVE LOGITS
    an
    1.08
    y
    0.83
    "
    0.82
    c
    0.78
     ailes
    0.77
    ं
    0.77
     miscon
    0.75
    ला
    0.74
    Chez
    0.73
    Bam
    0.73
    Activations Density 0.002%

    No Known Activations