© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 145543
    Prev
    Next
    INDEX
    Explanations

    controversy and scandals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    stat
    0.72
    strategies
    0.71
     تعاون
    0.68
     strategies
    0.68
     статисти
    0.67
    curves
    0.66
    бна
    0.66
     bầu
    0.64
    ඈ
    0.62
     கொரோ
    0.62
    POSITIVE LOGITS
     issue
    1.21
     matter
    1.01
     controversy
    1.00
     Issue
    0.99
     scam
    0.98
     row
    0.97
     Scam
    0.96
    issue
    0.94
     Controversy
    0.91
    Issue
    0.90
    Activations Density 0.003%

    No Known Activations