© 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. 29-GEMMASCOPE-2-RES-16K
    7. 1416
    Prev
    Next
    INDEX
    Explanations

    important notes disclaimer

    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_29_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
     kepada
    1.08
    到一个
    1.07
    到的
    1.03
    到了
    0.98
     naar
    0.95
     tot
    0.94
     unto
    0.92
    到
    0.89
     towards
    0.88
    ไปยัง
    0.85
    POSITIVE LOGITS
    ToBe
    1.80
     να
    1.39
     да
    1.21
    要
    1.19
     abz
    1.15
    ที่จะ
    1.10
    ທີ່ຈະ
    1.09
     să
    1.07
     要
    1.06
     einz
    1.01
    Activations Density 0.595%

    No Known Activations