© 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. 86750
    Prev
    Next
    INDEX
    Explanations

    pronoun followed by verb phrase

    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
     being
    -0.85
    initComponents
    -0.82
     endoc
    -0.80
     saranno
    -0.79
    țion
    -0.78
    ljen
    -0.77
    糖
    -0.77
     pertanto
    -0.77
     ऐसा
    -0.76
    зулта
    -0.74
    POSITIVE LOGITS
     discrepan
    0.97
     voces
    0.95
     usare
    0.92
     bucal
    0.89
     hubo
    0.87
     contraseña
    0.86
    monių
    0.86
    ͦ
    0.85
    ۟
    0.85
     поводу
    0.85
    Activations Density 0.020%

    No Known Activations