© 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. 72566
    Prev
    Next
    INDEX
    Explanations

    names like Malik and Karim

    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
    ",
    -2.75
    ,,
    -2.58
     Future
    -2.41
     большого
    -2.39
     ,
    -2.39
     Extending
    -2.34
    ,”
    -2.31
     Other
    -2.23
     Establishing
    -2.23
    .,
    -2.22
    POSITIVE LOGITS
    ໊
    2.58
    菝
    2.50
    
    2.41
    ࿆
    2.36
    皤
    2.31
    ⟝
    2.27
    𖥦
    2.27
     finde
    2.27
    Кита
    2.20
     wers
    2.19
    Activations Density 0.023%

    No Known Activations