© 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. 98227
    Prev
    Next
    INDEX
    Explanations

    neural network learning and training

    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
    nsic
    -0.84
    rý
    -0.80
     srdce
    -0.73
     kullanıcı
    -0.73
    Reb
    -0.72
     ブーツ
    -0.71
     limpar
    -0.71
     löytyy
    -0.71
     భూ
    -0.70
    惡
    -0.70
    POSITIVE LOGITS
     training
    2.05
     neuron
    1.95
     neurons
    1.94
     neural
    1.89
     learning
    1.81
     Neural
    1.80
    training
    1.58
    Neural
    1.58
     neuro
    1.55
     Learning
    1.51
    Activations Density 0.064%

    No Known Activations