© 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. 10-GEMMASCOPE-RES-131K
    7. 865
    Prev
    Next
    INDEX
    Explanations

    minority groups or related concepts

    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
     ”
    -2.66
     vorigen
    -2.64
    ?”
    -2.39
    In
    -2.34
    好的
    -2.30
     ewigen
    -2.30
     欣赏
    -2.28
     solidify
    -2.27
     Allgemeinen
    -2.23
     Ersten
    -2.23
    POSITIVE LOGITS
    酲
    2.88
    
    2.88
    
    2.67
    鵄
    2.66
     diki
    2.63
    喈
    2.61
    ープン
    2.36
    翆
    2.36
    ⽼
    2.36
    _
    2.34
    Activations Density 0.003%

    No Known Activations