© 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-IT
    3. 12-GEMMASCOPE-2-RES-16K
    4. 14687
    Prev
    Next
    INDEX
    Explanations

    foreign words

    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_12_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
    েও
    0.99
     Einige
    0.93
     Insgesamt
    0.93
     Акаде
    0.92
    mydb
    0.92
     hilfre
    0.91
    europa
    0.89
    
    0.88
     Ако
    0.86
    yyyy
    0.86
    POSITIVE LOGITS
     of
    1.14
    その
    1.02
     של
    0.96
    お
    0.95
     ແມ່ນ
    0.93
    เป็น
    0.91
    จะ
    0.86
    が
    0.86
     か
    0.86
    要
    0.84
    Activations Density 0.062%

    No Known Activations