© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 33056
    Prev
    Next
    INDEX
    Explanations

    intelligence and security agencies

    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
     装
    -0.79
    orail
    -0.77
    Buona
    -0.76
    انة
    -0.75
     bedingt
    -0.75
     Merz
    -0.75
    ễn
    -0.73
     inspected
    -0.73
     czeko
    -0.73
     DPRD
    -0.71
    POSITIVE LOGITS
     intelligence
    2.98
     Intelligence
    2.52
    Intelligence
    2.36
    intelligence
    2.36
     security
    1.97
     spy
    1.92
     Security
    1.77
     CIA
    1.68
     INTELL
    1.66
     inteligencia
    1.57
    Activations Density 0.043%

    No Known Activations