© 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. 17-GEMMASCOPE-2-RES-16K
    7. 6524
    Prev
    Next
    INDEX
    Explanations

    Roman numeral

    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_17_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
     hoping
    0.98
     letech
    0.91
     misused
    0.89
     kombin
    0.89
    🏼
    0.87
     augment
    0.86
     combin
    0.85
     Combin
    0.84
     indeed
    0.84
     قصد
    0.83
    POSITIVE LOGITS
    рат
    1.06
    atok
    0.99
    оні
    0.97
    م
    0.92
    el
    0.92
    vindo
    0.90
    са
    0.89
    癸
    0.88
    и
    0.88
    его
    0.87
    Activations Density 0.199%

    No Known Activations