© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 120621
    Prev
    Next
    INDEX
    Explanations

    `print` statements and code examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
     disminuir
    0.39
    酆
    0.38
     obesity
    0.37
     laziness
    0.37
     dismin
    0.37
    脌
    0.37
     decrease
    0.37
     perception
    0.36
     oplossing
    0.35
     proche
    0.35
    POSITIVE LOGITS
    \_
    0.45
     Calibration
    0.39
    utacji
    0.39
    လဲ
    0.38
     数据
    0.38
    联盟
    0.37
    來源
    0.37
    ೮
    0.37
    数据
    0.37
    ತೆಯ
    0.37
    Activations Density 0.017%

    No Known Activations