© 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. 1406
    Prev
    Next
    INDEX
    Explanations

    can draft reports

    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
     kunna
    3.79
    𝐞
    3.52
     putea
    3.25
     inevitably
    3.21
    𝐲
    3.11
     potuto
    2.89
    𝐢
    2.85
    ﺩ
    2.84
    ️
    2.82
     probabilmente
    2.72
    POSITIVE LOGITS
     hende
    3.40
     withstand
    3.33
    शीलता
    3.24
     gange
    2.90
    بع
    2.83
    kül
    2.82
    zonych
    2.81
    們
    2.79
     sogen
    2.76
     потребо
    2.72
    Activations Density 0.675%

    No Known Activations