© 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. 118519
    Prev
    Next
    INDEX
    Explanations

    airlines and airports

    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
    cripted
    -0.82
    tc
    -0.76
    sikan
    -0.76
    oltà
    -0.75
    borg
    -0.74
    Tracking
    -0.74
    Proxy
    -0.71
    alah
    -0.71
     Proxy
    -0.71
    PROXY
    -0.71
    POSITIVE LOGITS
     carriers
    1.16
     bilateral
    1.02
     Carriers
    0.97
     slot
    0.96
    cabo
    0.94
     carrier
    0.89
    hina
    0.86
    carrier
    0.83
     slots
    0.83
     airlines
    0.83
    Activations Density 0.019%

    No Known Activations