© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10814
    Prev
    Next
    INDEX
    Explanations

    linear activation unit

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

    activation functions like ReLU and sigmoid

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    鸚
    0.47
    纪念
    0.42
    眝
    0.42
    occhi
    0.41
     Karriere
    0.41
    レンダー
    0.40
    ഘടന
    0.40
    賢
    0.40
    モデル
    0.39
     PRICES
    0.39
    POSITIVE LOGITS
     activation
    0.98
     ReLU
    0.92
    ReLU
    0.91
    relu
    0.89
     activations
    0.87
     Activation
    0.82
    activation
    0.82
    Activation
    0.80
     activación
    0.79
     activate
    0.76
    Activations Density 0.005%

    No Known Activations