© 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. 119103
    Prev
    Next
    INDEX
    Explanations

    convolutional neural networks

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     remercie
    -0.75
    jeuner
    -0.74
    rildi
    -0.73
    affaires
    -0.71
    ladu
    -0.70
     Harcourt
    -0.69
    ု
    -0.69
    CREDIT
    -0.68
     CREDIT
    -0.68
    容量
    -0.68
    POSITIVE LOGITS
     max
    0.87
    Pooling
    0.83
    pool
    0.82
    Kim
    0.81
     convolution
    0.80
     Max
    0.78
    sentence
    0.77
    filter
    0.76
     pooling
    0.75
     Attention
    0.75
    Activations Density 0.009%

    No Known Activations