© 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
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10007
    Prev
    Next
    INDEX
    Explanations

    words with "ig"

    np_acts-logits-general · gemini-2.5-flash-lite

    rigidbody, trigger, rigorous, Jigglypuff

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kins
    0.40
    动的
    0.38
    崇
    0.37
     barely
    0.37
     संस्थानों
    0.36
    kut
    0.36
     دخل
    0.36
    麓
    0.36
    िफ
    0.35
    ედ
    0.35
    POSITIVE LOGITS
     ignition
    0.52
     ig
    0.51
    Ig
    0.51
    Pig
    0.50
    lesias
    0.50
    ignition
    0.49
     Ig
    0.49
    NORE
    0.48
     immunoglobulin
    0.47
     Wig
    0.46
    Activations Density 0.154%

    No Known Activations