© 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. 7120
    Prev
    Next
    INDEX
    Explanations

    expense, cost, financial matters

    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
       
    1.60
      
    1.52
        
    1.23
                                   
    1.16
         
    1.16
          
    1.06
    <i>
    1.01
           
    0.99
    …………………………………………
    0.99
    ‏
    0.92
    POSITIVE LOGITS
     experi
    1.54
     organiza
    1.49
     construc
    1.40
    ,<
    1.40
     hypersur
    1.40
     accom
    1.39
     ativid
    1.35
     informa
    1.35
     andRow
    1.35
     condi
    1.34
    Activations Density 0.069%

    No Known Activations