© 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. 104209
    Prev
    Next
    INDEX
    Explanations

    healthy individuals and tissues

    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
     lleve
    0.65
     。
    0.57
    Ｕ
    0.56
    ﻬ
    0.56
     levou
    0.55
    ORE
    0.55
    مبر
    0.55
    IRE
    0.54
    UM
    0.52
    م
    0.52
    POSITIVE LOGITS
     healthy
    0.59
    @
    0.57
    function
    0.57
    st
    0.56
    да
    0.56
    mois
    0.55
    <0x80>
    0.55
    à
    0.55
     Healthy
    0.54
     Triathlon
    0.54
    Activations Density 0.013%

    No Known Activations