© 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. 22-GEMMASCOPE-RES-131K
    4. 9760
    Prev
    Next
    INDEX
    Explanations

    he is talking about you

    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_22/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
     this
    -1.23
     your
    -1.15
     Isto
    -1.05
     heureux
    -1.04
     vetor
    -1.02
     keuangan
    -1.00
    entierung
    -1.00
    ео
    -0.98
     ramah
    -0.98
     istimewa
    -0.98
    POSITIVE LOGITS
     himself
    1.32
     sám
    1.18
     résister
    1.00
     خودش
    0.98
     insertar
    0.96
    なんですが
    0.93
    herself
    0.92
    
    0.92
     knows
    0.91
    もあります
    0.91
    Activations Density 0.002%

    No Known Activations