© 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. 65338
    Prev
    Next
    INDEX
    Explanations

    judicial titles and positions

    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
     bemerkt
    -1.58
     bewertet
    -1.35
    リュー
    -1.34
    ඍ
    -1.34
    arzt
    -1.34
    ový
    -1.34
     bemerken
    -1.33
    
    -1.33
     uygulama
    -1.31
     väldigt
    -1.30
    POSITIVE LOGITS
     by
    2.09
     if
    2.08
     one
    1.56
     of
    1.54
     out
    1.53
    嗚
    1.44
     said
    1.42
     when
    1.42
     still
    1.36
     using
    1.36
    Activations Density 0.068%

    No Known Activations