© 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. 15115
    Prev
    Next
    INDEX
    Explanations

    free of charge

    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
              
    -2.63
    ↵↵
    -2.44
            
    -2.34
    .
    -2.16
     \
    -2.14
     
    -2.06
          
    -2.02
                
    -1.95
                                
    -1.91
                                   
    -1.90
    POSITIVE LOGITS
    躂
    2.53
    ープン
    2.45
    ︓
    2.42
    沺
    2.34
    sudadera
    2.34
    袮
    2.30
     стоковые
    2.28
     изпол
    2.25
     стоковая
    2.22
    Wymiary
    2.19
    Activations Density 0.005%

    No Known Activations