© 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. 853
    Prev
    Next
    INDEX
    Explanations

    simplifying division of numerator

    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
    ্শন
    2.55
    
    2.50
    ্ম্ম
    2.43
    𝒊
    2.36
    𝖽
    2.35
    𝒆
    2.34
    िक्ट
    2.31
    ियां
    2.30
    اح
    2.22
    िणी
    2.20
    POSITIVE LOGITS
    MLA
    1.98
    affee
    1.96
     무
    1.92
    wo
    1.90
    로부터
    1.88
    Residents
    1.83
    chaft
    1.80
    Le
    1.78
     menampilkan
    1.74
    uvre
    1.74
    Activations Density 0.035%

    No Known Activations