© 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. 39176
    Prev
    Next
    INDEX
    Explanations

    uppercase abbreviations

    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
    淠
    -3.75
    姈
    -3.05
    泐
    -2.70
    ᥬ
    -2.61
    蘩
    -2.59
    疴
    -2.56
    骉
    -2.55
    
    -2.55
    
    -2.50
    脔
    -2.48
    POSITIVE LOGITS
    s
    4.25
     When
    3.00
     There
    2.89
     ก็
    2.61
    ]
    2.59
    ☎️
    2.48
    z
    2.48
     και
    2.41
    when
    2.38
     Когда
    2.31
    Activations Density 0.004%

    No Known Activations