© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 27876
    Prev
    Next
    INDEX
    Explanations

    online tools and calculators

    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
    க்கு
    0.54
    amaged
    0.51
    sten
    0.49
    enes
    0.48
    publication
    0.48
    <0x86>
    0.47
    ﻔ
    0.47
    <0x85>
    0.47
    asional
    0.47
    墙
    0.46
    POSITIVE LOGITS
     инструмент
    0.64
     оценки
    0.61
     herramienta
    0.57
     গুগল
    0.57
     Tool
    0.56
     Canva
    0.55
     câștig
    0.55
     beeindruck
    0.54
     گوگل
    0.54
     pesta
    0.54
    Activations Density 0.133%

    No Known Activations