© 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. 15089
    Prev
    Next
    INDEX
    Explanations

    sneak peek

    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
     But
    -3.53
                
    -3.45
            
    -3.25
    秝
    -3.14
    u
    -2.73
                                  
    -2.70
     cherish
    -2.58
    -2.58
           
    -2.52
     も
    -2.50
    POSITIVE LOGITS
    麪
    3.19
    囖
    3.05
    archiwizowane
    3.05
    沨
    3.00
    𖧵
    2.94
     стоковые
    2.86
    硨
    2.78
    Tetapi
    2.77
    iſe
    2.75
    ⬈
    2.70
    Activations Density 0.005%

    No Known Activations