© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 7287
    Prev
    Next
    INDEX
    Explanations

    at least

    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_22_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
    <u>
    1.43
      
    1.21
    <strong>
    1.18
         
    1.13
          
    1.11
     lug
    1.09
     没有
    1.08
             
    1.08
              
    1.06
       
    1.05
    POSITIVE LOGITS
    <0x0C>
    1.32
    www
    1.14
    WWW
    1.14
    Figure
    0.99
    䡒
    0.96
    Table
    0.95
    ‬‬
    0.95
    ®,
    0.95
    轪
    0.94
    !)
    0.93
    Activations Density 0.101%

    No Known Activations