© 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. 607
    Prev
    Next
    INDEX
    Explanations

    online resources and tools

    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
     ‘
    1.08
    ̜
    1.03
     Fighting
    1.01
     богат
    0.99
     paused
    0.98
    秉
    0.97
     Sake
    0.97
     FIGHT
    0.97
    瑁
    0.96
    ย์
    0.96
    POSITIVE LOGITS
    𝐦
    1.13
    𝐥
    1.06
    mier
    1.04
    w
    1.01
    wj
    1.01
    𝐯
    0.98
     "/"
    0.96
    mt
    0.94
    listItem
    0.93
    ///////////////
    0.92
    Activations Density 0.543%

    No Known Activations