© 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. 90193
    Prev
    Next
    INDEX
    Explanations

    URLs, GitHub, code repositories

    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
    elementAt
    -0.92
    Brent
    -0.79
     Breslau
    -0.79
     when
    -0.78
    UTF
    -0.77
     Lombar
    -0.75
     hote
    -0.75
     الطعام
    -0.75
    ());
    -0.74
    🍕
    -0.73
    POSITIVE LOGITS
     Tensor
    1.29
     GPUs
    1.16
     TensorFlow
    1.15
    Tensor
    1.14
     training
    1.13
    arxiv
    1.08
     entrenar
    1.08
     Nvidia
    1.06
    ToTensor
    1.05
     python
    1.05
    Activations Density 0.144%

    No Known Activations