© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 127885
    Prev
    Next
    INDEX
    Explanations

    questions and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     geha
    -1.19
     reizen
    -1.09
    klere
    -1.09
    issante
    -1.08
     its
    -1.08
    -};
    -1.04
     voetballer
    -1.03
    SceneManagement
    -1.02
     vakantie
    -1.01
     blessés
    -1.00
    POSITIVE LOGITS
                
    1.08
        
    1.05
     obviously
    1.02
              
    0.96
     tamen
    0.92
     doraemon
    0.91
                    
    0.90
    .
    0.90
            
    0.90
     presently
    0.90
    Activations Density 0.000%

    No Known Activations