© 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. 107245
    Prev
    Next
    INDEX
    Explanations

    aviation records and pioneers

    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
    炮
    -0.81
     sailing
    -0.77
     paddle
    -0.76
    軌道
    -0.76
    Sailing
    -0.76
     bike
    -0.73
     steam
    -0.73
    ExtendWith
    -0.72
     sailboat
    -0.71
     insertion
    -0.71
    POSITIVE LOGITS
     hangar
    1.00
     Amelia
    0.90
     печени
    0.88
     fuselage
    0.85
     Croydon
    0.85
    Amelia
    0.85
     aerob
    0.84
    Avi
    0.83
     airfield
    0.82
     Octave
    0.82
    Activations Density 0.033%

    No Known Activations