© 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. 83209
    Prev
    Next
    INDEX
    Explanations

    activation functions and mathematical operations

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

    The neuron strongly activates on mentions of neural‐network activation functions (e.g. “ReLU,” “tanh”).

    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
     acorn
    -0.82
    ENCER
    -0.79
    ILLES
    -0.78
     Acorn
    -0.77
     الحلقة
    -0.75
    🍪
    -0.75
    transpose
    -0.73
     sya
    -0.71
    gerät
    -0.71
     acorns
    -0.70
    POSITIVE LOGITS
     saturation
    0.96
    leak
    0.88
    関する
    0.81
     satur
    0.80
     Slo
    0.79
     leak
    0.79
     negative
    0.77
    lierten
    0.77
     inplace
    0.77
     leakage
    0.77
    Activations Density 0.009%

    No Known Activations