© 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. 22-GEMMASCOPE-2-RES-16K
    7. 1664
    Prev
    Next
    INDEX
    Explanations

    red and blue collocations

    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_22_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
     int
    0.85
    int
    0.84
     respons
    0.79
    用
    0.78
     posto
    0.74
    ara
    0.74
     quer
    0.73
    ron
    0.73
    Sparse
    0.73
     Pert
    0.72
    POSITIVE LOGITS
    色的
    1.78
     haired
    1.49
     foncé
    1.39
    색
    1.35
     اللون
    1.34
    oubt
    1.33
     رنگ
    1.33
    washing
    1.26
     நிற
    1.24
    emptive
    1.21
    Activations Density 0.292%

    No Known Activations