© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 2254
    Prev
    Next
    INDEX
    Explanations

    military and defense concepts

    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_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
    焦虑
    0.68
    诊
    0.68
    肿
    0.68
    消费者
    0.67
     Pediatrics
    0.67
    愔
    0.66
    💆
    0.66
    谪
    0.65
     Bạn
    0.64
    读者
    0.64
    POSITIVE LOGITS
     missile
    1.34
     military
    1.27
     missiles
    1.27
    軍
    1.20
    military
    1.20
     weapons
    1.15
     munitions
    1.13
     warships
    1.11
     NATO
    1.10
     militares
    1.09
    Activations Density 0.383%

    No Known Activations