© 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. 86997
    Prev
    Next
    INDEX
    Explanations

    "wheel" followed by a word

    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
    czegóły
    -1.05
    ↵
    -0.93
    }^\
    -0.89
     medži
    -0.88
     weak
    -0.86
    i
    -0.81
    ])){
    -0.79
    Même
    -0.78
    e
    -0.78
    +
    
    -0.77
    POSITIVE LOGITS
    barrow
    1.73
     Kullan
    1.05
     spokes
    1.03
    spin
    1.00
     Wheel
    0.98
    ersburg
    0.95
    幸运
    0.93
    ksiä
    0.91
    CHAIR
    0.91
    BASE
    0.91
    Activations Density 0.013%

    No Known Activations