© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39797
    Prev
    Next
    INDEX
    Explanations

    credit rating and situation

    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_22/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
     cucchiai
    -1.22
     poule
    -1.20
     כוס
    -1.09
    韁
    -1.09
     навсегда
    -1.09
    밈
    -1.02
     ہی
    -1.02
     salade
    -1.00
     frites
    -1.00
     מים
    -0.98
    POSITIVE LOGITS
     your
    1.96
     you
    1.60
     düşük
    1.32
     risk
    1.30
    ֶּ
    1.27
     факторов
    1.24
    ندية
    1.24
     umumnya
    1.23
     брюки
    1.23
     biasanya
    1.23
    Activations Density 0.027%

    No Known Activations