© 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. 75535
    Prev
    Next
    INDEX
    Explanations

    hidden layers

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

    The neuron detects mentions of neural network architecture setup, especially specifications of layer sizes (e.g. “64 nodes in the first layer”).

    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
    北
    -0.70
    美子
    -0.68
     nunca
    -0.67
    嚢
    -0.67
     stabbing
    -0.66
    디오
    -0.66
     phạm
    -0.63
     complain
    -0.63
    ┛
    -0.63
    хождения
    -0.62
    POSITIVE LOGITS
     hidden
    2.23
    hidden
    2.11
     layers
    1.98
    Hidden
    1.95
     layer
    1.92
    layers
    1.84
     Hidden
    1.84
    HIDDEN
    1.83
    layer
    1.75
     Layer
    1.74
    Activations Density 0.024%

    No Known Activations