© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 4284
    Prev
    Next
    INDEX
    Explanations

    tests and testing

    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_29_width_65k_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
    Minecraft
    0.65
    徙
    0.65
    اہد
    0.62
    zeugung
    0.61
     నట
    0.60
    Instantiation
    0.59
    ígenes
    0.59
    চন
    0.59
    橱
    0.59
     conséquent
    0.59
    POSITIVE LOGITS
     tests
    2.62
     testing
    2.59
     Testing
    2.39
     test
    2.33
     Tests
    2.32
    Testing
    2.26
    Tests
    2.20
    tests
    2.19
    测试
    2.17
    testing
    2.13
    Activations Density 0.176%

    No Known Activations