© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 24083
    Prev
    Next
    INDEX
    Explanations

    Paris Saint-Germain generation parameters

    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
     Coventry
    0.37
     मामा
    0.36
    Birmingham
    0.36
     خاصيه
    0.36
     भावनाओं
    0.36
     Fleet
    0.36
    ﻙ
    0.36
     есте
    0.35
    )_{(
    0.35
    स्‍
    0.35
    POSITIVE LOGITS
    PSG
    0.59
     PSG
    0.58
     Parigi
    0.48
     ps
    0.46
     Paris
    0.46
    paris
    0.46
     Pary
    0.44
     paris
    0.44
    Paris
    0.43
     synchrotron
    0.43
    Activations Density 0.003%

    No Known Activations