© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 3002
    Prev
    Next
    INDEX
    Explanations

    nuclear weapons and war

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     BAFF
    0.41
     individui
    0.39
     injurious
    0.37
     الألم
    0.37
     Willis
    0.36
    vres
    0.35
    vrir
    0.35
     મંદ
    0.35
    parsedBlock
    0.35
    確
    0.35
    POSITIVE LOGITS
     weapons
    0.59
     weapon
    0.52
    核
    0.52
     Weapons
    0.51
    weapons
    0.48
     fission
    0.47
    武器
    0.47
     核
    0.47
    armed
    0.46
     অস্ত্রের
    0.46
    Activations Density 0.045%

    No Known Activations