© 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. 50198
    Prev
    Next
    INDEX
    Explanations

    plastic stamping

    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
     ciudadano
    -0.82
    rha
    -0.82
    ஞ்ச
    -0.82
     šal
    -0.81
     citizens
    -0.81
    
    -0.79
     sponsoring
    -0.78
    matorium
    -0.78
    recated
    -0.75
     citizenship
    -0.75
    POSITIVE LOGITS
    ̧
    0.82
    shapes
    0.81
     Bous
    0.78
     Martinique
    0.77
     Waterman
    0.76
    restore
    0.76
    لاس
    0.74
     Died
    0.73
    aney
    0.73
    ヒト
    0.73
    Activations Density 0.009%

    No Known Activations