© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 14783
    Prev
    Next
    INDEX
    Explanations

    met with or means

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ্লে
    1.41
    Appellant
    1.37
    sentiment
    1.36
    ს
    1.35
    кана
    1.31
    یف
    1.31
    ණ
    1.28
    образ
    1.26
    ফুজ
    1.24
    ا
    1.24
    POSITIVE LOGITS
    ட்டிக்
    1.72
    ックレス
    1.71
     greenhouse
    1.62
     الصحة
    1.62
    複製
    1.62
    টিআই
    1.61
     dezembro
    1.60
     nóng
    1.60
     khắp
    1.59
    幾個
    1.59
    Activations Density 20.239%

    No Known Activations