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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 13611
    Prev
    Next
    INDEX
    Explanations

    military service and recruitment

    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_262k_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
    善
    0.46
     utilisées
    0.46
     softmax
    0.46
    setup
    0.45
    高速
    0.45
    inosaur
    0.44
     sticky
    0.44
     bokeh
    0.44
     diamètre
    0.44
    堆
    0.44
    POSITIVE LOGITS
     enlist
    1.02
     military
    0.89
     recrut
    0.89
     volunteering
    0.87
     militares
    0.86
     Military
    0.84
     enlisted
    0.83
     recruiter
    0.80
     militaires
    0.80
     militaire
    0.78
    Activations Density 0.033%

    No Known Activations