© 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. 822
    Prev
    Next
    INDEX
    Explanations

    start of while loop

    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
    स्पति
    3.13
    पु
    3.06
    아야
    2.80
    oster
    2.72
    ängen
    2.70
    THREE
    2.69
    𝚍
    2.58
    ︎
    2.57
    enzie
    2.57
    ifiable
    2.52
    POSITIVE LOGITS
    s
    2.95
    ০
    2.84
     forwards
    2.57
    sby
    2.52
    ು
    2.49
    ओं
    2.47
    ","/
    2.46
    ات
    2.46
    ष्‍
    2.44
    romyalgia
    2.43
    Activations Density 0.759%

    No Known Activations