© 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. 60433
    Prev
    Next
    INDEX
    Explanations

    theoretical computer science and statistics

    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
    装修
    -0.83
    foot
    -0.79
    zone
    -0.75
    历史
    -0.70
    ina
    -0.68
    ylene
    -0.67
     asked
    -0.67
     tell
    -0.67
     told
    -0.65
    inem
    -0.65
    POSITIVE LOGITS
    artificial
    0.90
     Household
    0.88
    lardan
    0.85
     знать
    0.82
    isesti
    0.81
     Artificial
    0.80
     freshmen
    0.79
    umentos
    0.78
    Artificial
    0.77
     intruder
    0.77
    Activations Density 0.012%

    No Known Activations