© 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-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5471
    Prev
    Next
    INDEX
    Explanations

    Japanese greetings and responses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_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
     ବି
    0.98
     ଗ
    0.97
    abhave
    0.94
     ଯ
    0.93
     adopting
    0.93
    କୁ
    0.93
     melaksanakan
    0.93
     因此
    0.91
     alleging
    0.91
    ifference
    0.90
    POSITIVE LOGITS
    この
    1.20
    お
    1.18
    特に
    1.07
    少し
    1.06
    また
    1.05
    これは
    1.03
    ト
    1.01
    も
    1.01
    ただし
    0.99
    ハ
    0.99
    Activations Density 0.012%

    No Known Activations