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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 17681
    Prev
    Next
    INDEX
    Explanations

    penetration and targeted shots

    np_acts-logits-general · gemini-2.5-flash-lite

    penetration or stopping power

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     guns
    1.04
     firearms
    1.04
     gun
    0.97
    枪
    0.96
     firearm
    0.95
     बंदूक
    0.94
     Guns
    0.93
     GUN
    0.91
    銃
    0.90
     pistols
    0.88
    POSITIVE LOGITS
     penetration
    0.66
     penetrating
    0.64
     penetrate
    0.61
     penetrates
    0.61
     Penet
    0.57
     terminal
    0.55
    penet
    0.55
     grouped
    0.54
     penet
    0.54
     devastating
    0.53
    Activations Density 0.027%

    No Known Activations