© 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. 40-GEMMASCOPE-2-RES-262K
    7. 213016
    Prev
    Next
    INDEX
    Explanations

    friendly international matches

    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
     predstav
    0.38
     představ
    0.38
    主持
    0.37
    극
    0.37
    푦
    0.37
     মাঠে
    0.36
    喋
    0.36
     আহমে
    0.36
     Cellular
    0.36
     tidur
    0.36
    POSITIVE LOGITS
     friendly
    1.51
     Friendly
    1.50
    Friendly
    1.48
    friendly
    1.41
     freund
    1.13
     amist
    1.10
    友好
    1.07
     FRIEND
    1.07
     friendliness
    1.06
    友
    1.03
    Activations Density 0.006%

    No Known Activations