© 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. 2288
    Prev
    Next
    INDEX
    Explanations

    affluent geographic locations

    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
     engulfed
    3.00
    genden
    2.96
     sanguí
    2.86
     alloc
    2.79
    <bos>
    2.79
     elucidate
    2.70
     аналоги
    2.61
    이를
    2.60
     отде
    2.58
    ILE
    2.58
    POSITIVE LOGITS
     thaliana
    4.55
    sterdam
    3.35
     bxa
    3.26
    ERICAN
    2.94
     riscos
    2.93
    lyrics
    2.92
    랠
    2.89
    িকাংশ
    2.89
     Đây
    2.88
    ricult
    2.85
    Activations Density 2.109%

    No Known Activations