© 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. 54343
    Prev
    Next
    INDEX
    Explanations

    State secretary

    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
    ישראל
    -0.81
     minde
    -0.71
     Spanien
    -0.70
    }{*}{}
    -0.69
    девушка
    -0.68
     essentiels
    -0.68
     čast
    -0.68
     setCode
    -0.68
    ANDRE
    -0.68
    じゃん
    -0.67
    POSITIVE LOGITS
     State
    2.88
     Secretary
    2.63
    State
    2.22
    Secretary
    2.06
     secretary
    1.90
     STATE
    1.70
     Department
    1.63
     Государ
    1.60
    STATE
    1.57
    secretary
    1.47
    Activations Density 0.059%

    No Known Activations