© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 13067
    Prev
    Next
    INDEX
    Explanations

    fashion industry, adult-use, most possible purpose, game once, Money20/20Asia, state member

    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
    墬
    -2.19
    以上です
    -2.16
    というわけで
    -2.16
    ↑↑↑</
    -2.06
    他们在
    -2.00
     ended
    -1.95
    ではでは
    -1.88
     both
    -1.84
     були
    -1.83
     went
    -1.81
    POSITIVE LOGITS
     miniaturka
    2.38
    齪
    2.11
    perhaps
    2.11
     несмотря
    2.06
    
    2.05
     لقد
    2.03
    \'{
    2.00
    蚨
    1.99
    鲠
    1.99
     إنه
    1.97
    Activations Density 0.035%

    No Known Activations