© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64889
    Prev
    Next
    INDEX
    Explanations

    persecution, purges, repression

    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
    דות
    -0.77
    Overs
    -0.75
    sug
    -0.74
     kiệm
    -0.73
     Lieder
    -0.73
    偻
    -0.72
    מני
    -0.71
     NICH
    -0.71
    TBS
    -0.70
    чности
    -0.70
    POSITIVE LOGITS
     persecution
    4.31
     persecuted
    3.59
     persecu
    2.94
     persec
    2.81
     perse
    2.64
     persegu
    2.33
     repression
    2.20
     prosecution
    2.09
    迫
    2.03
    secution
    1.96
    Activations Density 0.061%

    No Known Activations