© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112278
    Prev
    Next
    INDEX
    Explanations

    mark

    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
    ,
    -2.98
    {
    -2.31
    
    -2.28
    ка
    -2.08
     exhausting
    -2.05
    }
    -2.03
     寬
    -1.89
    
    -1.89
    annica
    -1.88
    栊
    -1.88
    POSITIVE LOGITS
    '
    2.22
    os
    2.20
    pulseira
    2.20
    螃
    2.19
     marcato
    2.08
    ↑↑↑</
    2.00
     tehdä
    1.97
    щита
    1.93
    k
    1.93
     ausencia
    1.91
    Activations Density 0.055%

    No Known Activations