© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 131009
    Prev
    Next
    INDEX
    Explanations

    technical or scientific terms followed by specifics

    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_22/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
     cliquez
    -0.94
    делки
    -0.94
     profils
    -0.93
    queles
    -0.93
    premier
    -0.90
     manifiesta
    -0.89
     reação
    -0.89
     padrões
    -0.86
     plán
    -0.86
    redmi
    -0.86
    POSITIVE LOGITS
     olarak
    0.79
    there
    0.78
     ethernet
    0.77
    nesse
    0.75
    🏻
    0.75
    ammlung
    0.74
    ené
    0.74
    badlogic
    0.74
    viesa
    0.74
    מת
    0.73
    Activations Density 0.102%

    No Known Activations