© 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. 11737
    Prev
    Next
    INDEX
    Explanations

    line numbers

    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
     Arctic
    1.20
     D
    1.16
     Greek
    1.13
     Earth
    1.13
     Antarctic
    1.13
     TV
    1.09
    1
    1.09
     Persian
    1.06
     Yogurt
    1.06
     Film
    1.05
    POSITIVE LOGITS
    是以
    1.04
    with
    1.00
     durchaus
    0.98
    که
    0.96
    assume
    0.96
     faites
    0.92
    Ａ
    0.92
    getFile
    0.92
    OnFileChange
    0.92
    dengan
    0.91
    Activations Density 0.431%

    No Known Activations