© 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. 8280
    Prev
    Next
    INDEX
    Explanations

    employment discrimination and retaliation claims

    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
    ennung
    -1.28
    albeit
    -1.27
     biß
    -1.27
    considerable
    -1.16
     להיות
    -1.16
    而来
    -1.15
    رها
    -1.13
     TÉCNICA
    -1.13
     Besøkt
    -1.12
    pecabe
    -1.11
    POSITIVE LOGITS
    ใช้งาน
    1.26
    三月
    1.26
    ก็
    1.25
    有一个
    1.25
    需要
    1.25
    从
    1.22
     Workplace
    1.18
     家具
    1.18
     i
    1.17
     need
    1.17
    Activations Density 0.044%

    No Known Activations