© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 11124
    Prev
    Next
    INDEX
    Explanations

    various languages, topics, or symbols

    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
     trong
    1.12
     في
    1.10
    在她
    1.07
    在
    1.06
     në
    1.04
    ใน
    1.04
     در
    1.03
    在一个
    1.00
    在他的
    1.00
     فى
    0.99
    POSITIVE LOGITS
     guise
    1.10
     midst
    1.02
     וב
    0.95
     vicinity
    0.89
    𝖔
    0.88
     rámci
    0.86
     labyr
    0.85
    scattering
    0.83
     causado
    0.78
    𝖆
    0.75
    Activations Density 0.131%

    No Known Activations