© 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. 17-GEMMASCOPE-2-RES-16K
    7. 11249
    Prev
    Next
    INDEX
    Explanations

    family contributions

    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
    ည်း
    0.84
     இன்னொரு
    0.78
     університету
    0.76
     Dubai
    0.73
     UAE
    0.72
    ศาสตร์
    0.70
     Emirati
    0.70
    ：
    0.69
    க்கூட
    0.69
    публи
    0.69
    POSITIVE LOGITS
     बच्चो
    0.94
     amt
    0.94
     이용하여
    0.90
    рос
    0.88
     মতি
    0.86
     skilful
    0.86
     نمود
    0.86
    ালী
    0.85
     skillful
    0.84
    awas
    0.84
    Activations Density 0.019%

    No Known Activations