© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1206
    Prev
    Next
    INDEX
    Explanations

    code snippets and delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
     BAG
    1.02
    <unused1738>
    1.01
     SPIR
    0.97
     BOR
    0.97
     psychiatry
    0.94
     liturg
    0.94
     hates
    0.94
     matriline
    0.94
     terapeut
    0.93
     Igbo
    0.93
    POSITIVE LOGITS
    ```
    1.69
        
    1.55
            
    1.45
                
    1.40
    复制代码
    1.35
    </code>
    1.31
    <unused60>
    1.30
          
    1.29
    <!--
    1.28
    =======
    1.27
    Activations Density 0.052%

    No Known Activations