© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 14311
    Prev
    Next
    INDEX
    Explanations

    military force and action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
     darah
    1.15
    כים
    1.13
     clog
    1.03
     vomit
    1.01
     ses
    0.99
    rg
    0.96
     "|"
    0.94
    ті
    0.92
     elementary
    0.91
    et
    0.91
    POSITIVE LOGITS
    燹
    1.15
    쓱
    1.06
     coup
    1.05
    srand
    1.01
    ikap
    1.01
    गेशन
    1.00
    人を
    0.97
    ணம்
    0.97
    ご購入
    0.97
     रिजर्व
    0.93
    Activations Density 0.028%

    No Known Activations