© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 50962
    Prev
    Next
    INDEX
    Explanations

    neurons and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ռ
    0.41
     Grading
    0.41
     convolutional
    0.40
     pretrained
    0.40
     Weight
    0.39
     Convolution
    0.39
     насле
    0.39
    ImageLayout
    0.39
    畳
    0.39
    हरादून
    0.38
    POSITIVE LOGITS
    neurons
    0.68
     neurons
    0.67
     neuron
    0.58
    units
    0.55
     units
    0.54
    ユニット
    0.54
    neuron
    0.54
    Neurons
    0.53
     unités
    0.52
     hid
    0.52
    Activations Density 0.059%

    No Known Activations