© 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. 102651
    Prev
    Next
    INDEX
    Explanations

    person named Lucas

    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
    бурге
    -2.69
    
    -2.64
     dieß
    -2.47
    的血
    -2.34
    狁
    -2.30
     они
    -2.27
    
    -2.25
     سیستم
    -2.19
    鲵
    -2.17
    bedien
    -2.16
    POSITIVE LOGITS
    a
    3.28
    2.94
     has
    2.73
     be
    2.66
            
    2.64
          
    2.52
    )";
    2.47
     he
    2.45
     Our
    2.44
    are
    2.41
    Activations Density 0.001%

    No Known Activations