© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 3036
    Prev
    Next
    INDEX
    Explanations

    german language constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_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
    хема
    0.53
    󰡔
    0.50
    ⅙
    0.50
    的的
    0.48
    0
    0.47
    치의
    0.47
     hypotension
    0.46
    ;',
    0.46
    ROUND
    0.46
     bandage
    0.45
    POSITIVE LOGITS
     Mereka
    0.66
     می
    0.60
     werden
    0.56
     وج
    0.55
    ခဲ့
    0.55
    وت
    0.54
     می‌
    0.54
     Artists
    0.54
     mereka
    0.53
     Finds
    0.52
    Activations Density 0.005%

    No Known Activations