© 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. 34-GEMMASCOPE-RES-131K
    7. 91212
    Prev
    Next
    INDEX
    Explanations

    LA Times and Weekly

    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_34/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
    cemia
    -0.90
     maravilhoso
    -0.86
    顯示
    -0.85
    Pgina
    -0.83
    颶
    -0.82
     řešení
    -0.81
     anecd
    -0.80
    ộp
    -0.79
     Unternehmer
    -0.79
    はこんな感じ
    -0.78
    POSITIVE LOGITS
     County
    1.66
     Times
    1.56
     county
    1.45
    Times
    1.35
     COUNTY
    1.31
     times
    1.25
    County
    1.25
     TIMES
    1.13
     LA
    1.09
     Lakers
    1.09
    Activations Density 0.012%

    No Known Activations