© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 23639
    Prev
    Next
    INDEX
    Explanations

    mocking/stubbing dependencies

    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
    菖
    0.39
     공식
    0.38
     формате
    0.38
     Ritual
    0.38
    に追加
    0.38
     распростра
    0.38
    䣼
    0.37
     numeracy
    0.37
    捃
    0.37
     जोड़
    0.37
    POSITIVE LOGITS
     mock
    1.70
    mock
    1.60
     mocked
    1.59
    Mock
    1.57
     mocks
    1.52
     Mock
    1.51
     mocking
    1.35
    mocks
    1.24
     fake
    1.21
     mockup
    1.16
    Activations Density 0.013%

    No Known Activations