© 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. 31-GEMMASCOPE-2-RES-16K
    7. 9547
    Prev
    Next
    INDEX
    Explanations

    start of code conditions

    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_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     गाँधी
    1.41
    Whilst
    1.40
     Whilst
    1.27
    ２
    1.25
    １
    1.23
     ١
    1.22
     মোঃ
    1.16
    ١
    1.13
    ๑
    1.13
     हूँ
    1.12
    POSITIVE LOGITS
     अा
    0.95
     yüzde
    0.93
     —
    0.90
     பிரச்
    0.85
    さまざまな
    0.85
     지난해
    0.82
     nong
    0.82
    ziehungs
    0.80
     উত্প
    0.79
     உள்ப
    0.78
    Activations Density 0.006%

    No Known Activations