© 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. 16-GEMMASCOPE-2-RES-262K
    7. 117164
    Prev
    Next
    INDEX
    Explanations

    relative clause

    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
    r
    0.66
    ﻬ
    0.59
    ร
    0.59
    open
    0.56
    tra
    0.55
    ر
    0.54
    system
    0.52
    რ
    0.50
    R
    0.50
    terms
    0.49
    POSITIVE LOGITS
     LHC
    0.59
     αλλά
    0.58
    <unused2014>
    0.57
     ɛ
    0.57
     ẞ
    0.56
     Elaine
    0.55
    تحان
    0.55
     anticancer
    0.55
     amici
    0.54
     benchmarking
    0.54
    Activations Density 0.001%

    No Known Activations