© 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. 59271
    Prev
    Next
    INDEX
    Explanations

    mathematical theory concepts

    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
     argument
    -0.96
     Derivation
    -0.81
     sarebbe
    -0.80
    argument
    -0.80
     uitgevoerd
    -0.79
     Temporal
    -0.79
     Disorders
    -0.79
     Alters
    -0.78
    ֶּ
    -0.77
     Psychol
    -0.76
    POSITIVE LOGITS
     natural
    1.04
    Estudio
    1.04
     objects
    1.03
     Study
    0.99
     studying
    0.96
    Study
    0.96
    Até
    0.94
     naturales
    0.93
     obstructions
    0.93
     изу
    0.92
    Activations Density 0.181%

    No Known Activations