© 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. 59681
    Prev
    Next
    INDEX
    Explanations

    unique or uni- prefix followed by noun

    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
            
    -2.28
    ";
    -2.22
                        
    -2.22
                    
    -2.19
    でも
    -2.13
     dasarnya
    -2.13
     istrinya
    -2.11
                  
    -2.09
    ,”
    -2.08
    那我
    -2.03
    POSITIVE LOGITS
     costuras
    2.44
    几个月
    2.27
     thing
    2.25
     dévelo
    2.22
    replyreport
    2.17
     —
    2.17
     pesados
    2.13
    棪
    2.09
     एवं
    2.09
     bepa
    2.08
    Activations Density 0.004%

    No Known Activations