© 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-262K
    7. 19402
    Prev
    Next
    INDEX
    Explanations

    scroll down to find option

    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
    Blurred
    0.50
     обеспечивает
    0.48
    Empty
    0.45
     обеспечи
    0.45
    че
    0.44
    Celebr
    0.44
    Providing
    0.44
    י
    0.43
     cardiomyocyte
    0.42
     poskyt
    0.42
    POSITIVE LOGITS
     frog
    0.42
    兇
    0.38
     brunes
    0.37
     logically
    0.37
    驟
    0.36
     thêm
    0.36
    sby
    0.36
     anot
    0.34
     карда
    0.34
     adjust
    0.34
    Activations Density 0.012%

    No Known Activations