© 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. 99208
    Prev
    Next
    INDEX
    Explanations

    words expressed by people

    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
                                   
    -1.42
     già
    -1.41
       
    -1.39
    ?
    -1.38
     '*
    -1.30
     защиты
    -1.30
        
    -1.30
     übere
    -1.27
              
    -1.27
     gebunden
    -1.27
    POSITIVE LOGITS
     after
    1.88
     felpa
    1.70
     maravillas
    1.69
    Bisous
    1.61
    𖥦
    1.60
     Meksi
    1.56
     Suecia
    1.55
    Недо
    1.52
     riuscito
    1.52
     organiza
    1.49
    Activations Density 0.178%

    No Known Activations