© 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. 16-GEMMASCOPE-2-RES-262K
    7. 11716
    Prev
    Next
    INDEX
    Explanations

    tie

    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_16_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
    ى
    1.91
    ன்
    1.73
    но
    1.50
    ни
    1.50
    ু
    1.38
    ني
    1.34
    л
    1.29
    тся
    1.27
    зе
    1.27
    ών
    1.23
    POSITIVE LOGITS
    can
    1.19
    Tie
    1.17
     ties
    1.16
     Ties
    1.13
     I
    1.07
    y
    1.06
    Eq
    0.97
    case
    0.95
     tie
    0.95
    യും
    0.93
    Activations Density 0.012%

    No Known Activations