© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 8951
    Prev
    Next
    INDEX
    Explanations

    war/hero/brave/powerful content/deeds/land

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects the Japanese technical term “形成” (meaning “forming” or “formation”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    만
    1.05
     그리고
    0.86
    만을
    0.81
    tir
    0.72
    、
    0.71
    ၤ
    0.71
    tır
    0.70
    ो
    0.69
    지
    0.68
     보여
    0.67
    POSITIVE LOGITS
     অবস্থায়
    0.91
    事が
    0.86
     অবস্থায়
    0.80
    ことは
    0.78
     জনে
    0.77
     ח
    0.77
     ವೇಳೆ
    0.75
    ્યું
    0.75
    طفال
    0.74
     것처럼
    0.74
    Activations Density 0.000%

    No Known Activations