© 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. 9-GEMMASCOPE-2-RES-16K
    7. 2927
    Prev
    Next
    INDEX
    Explanations

    abuse, upgrade, crisis

    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_9_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    s
    4.15
    nya
    3.95
    sd
    3.92
    sz
    3.89
    ska
    3.73
    tı
    3.69
    side
    3.59
    
    3.54
    اً
    3.53
    ly
    3.51
    POSITIVE LOGITS
    一个
    3.93
    ل
    3.88
    л
    3.35
    ⣀
    3.14
    थमिक
    3.01
    ित्र
    2.87
    ל
    2.83
    ش
    2.79
    地方
    2.75
    quela
    2.71
    Activations Density 0.198%

    No Known Activations