© 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
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 19566
    Prev
    Next
    INDEX
    Explanations

    foreign and technical terms

    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
    kannya
    0.37
    കളിൽ
    0.36
     Choosing
    0.34
     Ethics
    0.32
     regretted
    0.32
     Seite
    0.31
     After
    0.30
     î
    0.30
     underdog
    0.30
     Übersicht
    0.30
    POSITIVE LOGITS
    로
    0.38
    ﺭ
    0.35
    日
    0.34
    ﺮ
    0.34
    ﻧ
    0.33
    مبر
    0.33
     نظام
    0.33
     roche
    0.33
    ینو
    0.32
     قوانین
    0.32
    Activations Density 0.144%

    No Known Activations