© 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. 117972
    Prev
    Next
    INDEX
    Explanations

    dimensionality reduction embeddings

    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
     Dortmund
    -0.79
     величи
    -0.75
    Вер
    -0.75
    atividade
    -0.73
     biceps
    -0.73
    ర
    -0.72
    नो
    -0.71
     currentDate
    -0.70
    openzeppelin
    -0.69
     mutate
    -0.69
    POSITIVE LOGITS
     embedding
    1.12
     manifold
    1.05
    manifold
    1.02
     TS
    1.02
     perplex
    0.93
     ts
    0.90
     MDS
    0.89
     trustworthiness
    0.89
    MDS
    0.86
     neighbourhood
    0.85
    Activations Density 0.015%

    No Known Activations