© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128723
    Prev
    Next
    INDEX
    Explanations

    an example of

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
                    
    -1.64
     consulté
    -1.53
    apatalk
    -1.44
        
    -1.43
    ingdon
    -1.40
    \
    -1.40
     между
    -1.38
                
    -1.38
     jeśli
    -1.38
          
    -1.35
    POSITIVE LOGITS
     others
    1.73
     deri
    1.56
    haltung
    1.52
     morales
    1.48
    Toujours
    1.48
    儅
    1.48
     rapi
    1.47
     doctrina
    1.47
     Pusat
    1.46
     findBy
    1.45
    Activations Density 0.029%

    No Known Activations