© 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. 41-GEMMASCOPE-2-RES-262K
    7. 65954
    Prev
    Next
    INDEX
    Explanations

    bombs bursting in air

    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_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    holomorphic
    0.41
     اغ
    0.39
    薙
    0.38
    ద్ధ
    0.38
     Paglinawan
    0.38
    helloworld
    0.37
     tranche
    0.37
     పేర్కొ
    0.37
    SourceObject
    0.37
     प्रचंड
    0.37
    POSITIVE LOGITS
     fireworks
    1.62
     Fireworks
    1.55
    Fireworks
    1.44
     पटाखे
    1.25
     पटाखों
    1.16
    🎆
    1.13
    🎇
    1.12
     फटा
    0.81
    🧨
    0.77
     पटा
    0.68
    Activations Density 0.002%

    No Known Activations