© 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. 1816
    Prev
    Next
    INDEX
    Explanations

    log timestamps and codes

    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
    ()=>{
    3.41
    𝚘
    3.20
    𝚞
    3.15
    يء
    3.09
    ০০
    3.01
    ১৫
    2.88
    𝚣
    2.83
    𝚢
    2.77
    𝚔
    2.74
    𝚊
    2.74
    POSITIVE LOGITS
     mondial
    2.48
     delen
    2.37
    ും
    2.34
    ात
    2.26
    ْ
    2.24
    이션
    2.12
     machin
    2.12
    ਚ
    2.10
    וא
    2.06
    ্যান্ড
    2.05
    Activations Density 0.483%

    No Known Activations