© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6765
    Prev
    Next
    INDEX
    Explanations

    commercial clients

    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
    ዶ
    0.52
    ='',
    0.51
     alternatives
    0.50
    工作人员
    0.48
    Teacher
    0.47
    UserId
    0.47
     تصور
    0.47
    érios
    0.47
    č
    0.47
    Om
    0.47
    POSITIVE LOGITS
     clients
    3.11
     clientes
    2.80
     Clients
    2.77
    clients
    2.69
    Clients
    2.69
     клиентов
    2.64
     klien
    2.64
     clienti
    2.61
     client
    2.58
     клиен
    2.58
    Activations Density 0.284%

    No Known Activations