© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108263
    Prev
    Next
    INDEX
    Explanations

    Leicestershire Kansas Topeka Karnataka

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on occurrences of Java’s low‐level I/O package names and types (e.g. “java.nio”, “ByteBuffer”, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     Ө
    -0.74
    新竹
    -0.74
     Mun
    -0.70
    Hawks
    -0.69
     Shiraz
    -0.69
    cove
    -0.69
     Measuring
    -0.69
     drawable
    -0.68
    睫
    -0.68
     Gees
    -0.67
    POSITIVE LOGITS
     interest
    1.01
     Scattering
    0.88
     Topeka
    0.87
     Karnataka
    0.85
     Leicestershire
    0.85
     Kansas
    0.84
     selector
    0.78
     Leicester
    0.78
    bane
    0.77
    Leicester
    0.77
    Activations Density 0.002%

    No Known Activations