© 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. 17-GEMMASCOPE-2-RES-16K
    7. 3621
    Prev
    Next
    INDEX
    Explanations

    harm and destruction

    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_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
     ಅಪಾಯ
    1.00
    onacci
    0.98
     getc
    0.94
    agnetic
    0.89
    lensFlare
    0.87
     magnétique
    0.86
     بروز
    0.86
     rischio
    0.85
    帔
    0.85
    籹
    0.85
    POSITIVE LOGITS
     destruction
    1.21
     extermin
    1.19
     уничто
    1.15
     merciless
    1.12
     enemy
    1.07
     punishment
    1.05
     destru
    1.04
     Destruction
    1.03
     vanqu
    1.03
     destroying
    1.03
    Activations Density 0.237%

    No Known Activations