© 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. 31-GEMMASCOPE-2-RES-262K
    7. 10026
    Prev
    Next
    INDEX
    Explanations

    specific domains and subjects

    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_31_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
     збіль
    0.47
     或
    0.43
     первый
    0.41
    初始化
    0.38
    )。
    0.38
    pInBuffer
    0.38
     botao
    0.38
    或
    0.38
     दो
    0.38
     умень
    0.38
    POSITIVE LOGITS
     linguistics
    0.63
     aviation
    0.61
     robotics
    0.57
     journalism
    0.53
     electronics
    0.52
     cryptography
    0.50
    aviation
    0.50
     aerospace
    0.50
    healthcare
    0.50
     athletics
    0.50
    Activations Density 0.166%

    No Known Activations