© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 1536
    Prev
    Next
    INDEX
    Explanations

    sec, 2nd, nd

    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
    ്
    1.61
    िंग
    1.60
    ্ড
    1.49
    एं
    1.46
     esté
    1.40
     myosin
    1.37
     dispensed
    1.34
     doom
    1.33
    方に
    1.29
    ্ডি
    1.28
    POSITIVE LOGITS
    nd
    4.13
    thirds
    2.70
     nd
    2.62
     thirds
    2.51
    ND
    2.46
    ي
    2.26
    ت
    2.24
    nds
    2.14
    т
    1.95
    स्ताना
    1.92
    Activations Density 0.828%

    No Known Activations