© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10120
    Prev
    Next
    INDEX
    Explanations

    warfare and military conflict

    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
    镖
    0.47
    ثیر
    0.45
    立场
    0.44
    区别
    0.44
     الخدم
    0.43
     doraemon
    0.43
    愫
    0.43
     亻
    0.43
     Couleur
    0.43
    peicher
    0.42
    POSITIVE LOGITS
     battlefield
    0.64
     stalemate
    0.59
     losses
    0.59
     ridge
    0.57
     tactical
    0.56
     retreat
    0.56
     retreats
    0.55
     strategy
    0.53
     campaigns
    0.53
     victories
    0.53
    Activations Density 0.099%

    No Known Activations