© 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. 90411
    Prev
    Next
    INDEX
    Explanations

    Afghan official, Islamic Republic, Lady Gaga

    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
    Iranian
    -1.02
     Iranian
    -0.89
    Iran
    -0.78
     joaat
    -0.76
     Iran
    -0.74
     którzy
    -0.73
     вое
    -0.72
     Tehran
    -0.70
    ствовал
    -0.70
    isesti
    -0.69
    POSITIVE LOGITS
     (£
    0.81
    Зна
    0.79
     SPIE
    0.79
     statistical
    0.77
     trov
    0.77
    equations
    0.74
    🧖
    0.73
     искать
    0.73
    statistics
    0.72
     ejer
    0.72
    Activations Density 0.037%

    No Known Activations