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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 41-GEMMASCOPE-2-RES-65K
    4. 14495
    Prev
    Next
    INDEX
    Explanations

    lymph and lymphatic

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
     নও
    0.57
    inputType
    0.56
    定量
    0.55
    ிரி
    0.54
    趵
    0.54
     Moroccan
    0.53
     Tenerife
    0.53
     थर
    0.53
    ড়ান্ত
    0.53
    醸
    0.53
    POSITIVE LOGITS
     lymph
    2.94
     Lymph
    2.78
     lymphatic
    2.69
    Lymph
    2.69
    lymph
    2.64
     lym
    2.48
     lymphoid
    2.14
     linf
    2.14
     lymphatiques
    2.05
     lymphoma
    1.82
    Activations Density 0.039%

    No Known Activations