© 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. 15641
    Prev
    Next
    INDEX
    Explanations

    predicting following words in phrases

    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
    Inflation
    1.69
     Detox
    1.68
     NADPH
    1.67
    鏄
    1.67
    slidesPer
    1.61
    اء
    1.58
    鈽
    1.58
     SmackDown
    1.56
    䔀
    1.54
     interferon
    1.52
    POSITIVE LOGITS
    ‌ترین
    2.34
    ভাবে
    2.07
    idade
    1.98
    mente
    1.85
     ترین
    1.85
    ness
    1.79
    emente
    1.73
    iteit
    1.69
    ‌تر
    1.66
    idad
    1.65
    Activations Density 0.251%

    No Known Activations