© 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. 83090
    Prev
    Next
    INDEX
    Explanations

    childhood learning experiences

    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
    lorette
    -0.91
     husband
    -0.88
     kobiet
    -0.87
    站起来
    -0.87
    合适
    -0.87
     colleagues
    -0.87
     Colleagues
    -0.87
     девушки
    -0.86
     рассла
    -0.85
     colleg
    -0.85
    POSITIVE LOGITS
     preco
    1.50
     ask
    1.17
    preco
    1.15
     asked
    1.12
     unsupervised
    1.10
     learning
    1.08
     playing
    1.08
    Preco
    1.07
     learn
    1.05
     children
    1.03
    Activations Density 0.054%

    No Known Activations