© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 2061
    Prev
    Next
    INDEX
    Explanations

    challenging the usual narrative

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_16k_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
    ed
    1.05
    ﺔ
    0.94
    ﺩ
    0.93
    ﻴ
    0.90
    ird
    0.89
     thoroughly
    0.88
    ة
    0.88
    ares
    0.87
     decidedly
    0.86
    ﺖ
    0.85
    POSITIVE LOGITS
     pengelolaan
    1.11
     Wirkung
    1.10
     Nutzung
    1.04
     aspects
    1.03
     zarówno
    1.03
     Paglin
    1.02
     amacıyla
    1.02
     Более
    1.01
    ită
    1.01
     Existen
    1.00
    Activations Density 0.445%

    No Known Activations