© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9143
    Prev
    Next
    INDEX
    Explanations

    terrorist activities or Afghanistan

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Viber
    0.61
     Belarusian
    0.58
     referendum
    0.56
     Belarus
    0.56
     Yerevan
    0.56
    搶
    0.56
     Magyar
    0.53
     ceasefire
    0.53
     Eurovision
    0.53
    }^{-\
    0.52
    POSITIVE LOGITS
     terrorist
    1.27
     terrorism
    1.26
    terrorism
    1.19
     Terrorism
    1.16
     Afghanistan
    1.16
    Afghanistan
    1.15
     Osama
    1.11
     terrorists
    1.10
     Terror
    1.09
    Terror
    1.09
    Activations Density 0.080%

    No Known Activations