© 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
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 15082
    Prev
    Next
    INDEX
    Explanations

    korean polite sentence endings

    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
    と
    0.89
    に
    0.86
    च्या
    0.82
     का
    0.81
     से
    0.81
    का
    0.80
     হলো
    0.79
     سے
    0.78
    を
    0.78
    nya
    0.77
    POSITIVE LOGITS
     queste
    1.01
     poeta
    0.98
     dinheiro
    0.98
     artigo
    0.96
     questi
    0.93
     Estos
    0.92
     humili
    0.92
     escritores
    0.92
     évent
    0.91
     boissons
    0.91
    Activations Density 0.001%

    No Known Activations