© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 11647
    Prev
    Next
    INDEX
    Explanations

    religious figures and purgatory

    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
    𖣘
    -1.90
    s
    -1.78
     jadi
    -1.70
    薆
    -1.69
    gendes
    -1.62
    嫪
    -1.62
     myriad
    -1.60
    ipel
    -1.56
    tiness
    -1.55
    毉
    -1.55
    POSITIVE LOGITS
    )$
    1.59
    ريل
    1.58
    </h4>
    1.58
     servem
    1.56
    ل
    1.53
     possuem
    1.41
     antigas
    1.41
    ']
    
    1.39
     ケース
    1.38
     dão
    1.38
    Activations Density 0.008%

    No Known Activations