© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 14064
    Prev
    Next
    INDEX
    Explanations

    Python `__init__` method

    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
    ঁচ
    1.88
    ্ঠ
    1.88
    ك
    1.86
    كت
    1.86
    ستہ
    1.76
     нав
    1.76
    жник
    1.76
     अधिवेशन
    1.75
    راق
    1.75
     เอ่อ
    1.75
    POSITIVE LOGITS
    addTask
    2.39
    asInstanceOf
    2.31
     श्रीनगर
    2.13
    ΙΚ
    2.10
    ᅪ
    2.01
    bgColor
    1.99
    食
    1.99
    ઢી
    1.99
    romax
    1.98
    isDebug
    1.98
    Activations Density 0.064%

    No Known Activations