© 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. 103131
    Prev
    Next
    INDEX
    Explanations

    optimization and invention

    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
    我们
    -1.08
     бампер
    -1.06
    我們
    -0.96
    应该
    -0.93
    いずれ
    -0.91
     उदाहरण
    -0.91
    ूस
    -0.89
    👣
    -0.89
    我们可以
    -0.89
     chronique
    -0.89
    POSITIVE LOGITS
     doesn
    1.43
     didn
    1.40
     lasted
    1.24
     lasts
    1.24
     my
    1.23
     leaves
    1.20
     does
    1.17
     feel
    1.14
     definitely
    1.13
     feels
    1.13
    Activations Density 0.010%

    No Known Activations