© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10151
    Prev
    Next
    INDEX
    Explanations

    e-commerce and streaming platforms

    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_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
     SK
    0.48
     prot
    0.43
     menyes
    0.41
     부
    0.39
     accessories
    0.38
     스타일
    0.38
     THOR
    0.38
     agreeable
    0.37
     BK
    0.37
     popular
    0.37
    POSITIVE LOGITS
     jobNumber
    0.42
     raping
    0.42
     இருப்பதால்
    0.42
    ждая
    0.41
    веря
    0.40
    ollary
    0.40
    Spending
    0.40
    燔
    0.40
     bringing
    0.40
    oną
    0.40
    Activations Density 0.008%

    No Known Activations