© 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-3-1B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 5941
    Prev
    Next
    INDEX
    Explanations

    potential harm and trauma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     favors
    0.73
     वगैरह
    0.68
     anything
    0.66
     Basically
    0.64
    Basically
    0.64
     favoring
    0.64
     leisurely
    0.63
    [^
    0.63
     వ్య
    0.62
    fav
    0.62
    POSITIVE LOGITS
     trauma
    1.01
     stigma
    0.96
     traumat
    0.94
     PTSD
    0.92
     grieving
    0.91
     remembrance
    0.89
     TRIGGER
    0.88
     victims
    0.88
     traum
    0.87
     perpetrator
    0.87
    Activations Density 1.330%

    No Known Activations