© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 1692
    Prev
    Next
    INDEX
    Explanations

    css rgba colors

    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
    ا
    2.42
    روں
    2.15
    nętr
    2.05
    اون
    1.98
    enek
    1.96
    的能力
    1.96
    لای
    1.92
     وتع
    1.90
     وتح
    1.89
    에
    1.88
    POSITIVE LOGITS
    {#
    2.11
    ouncements
    2.09
    wedge
    2.07
     hồi
    2.07
    ᴹ
    2.03
    しく
    2.00
     वापसी
    1.91
     fhe
    1.87
    blockSize
    1.87
    धर
    1.87
    Activations Density 0.000%

    No Known Activations