© 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. 27937
    Prev
    Next
    INDEX
    Explanations

    counts of patients

    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
    berus
    -0.90
    arest
    -0.86
     influencia
    -0.85
    秝
    -0.84
    чих
    -0.83
    colata
    -0.83
    relevance
    -0.82
     ór
    -0.82
     Moines
    -0.82
     lainnya
    -0.81
    POSITIVE LOGITS
     Selv
    0.91
    Sel
    0.90
     основном
    0.90
    RED
    0.89
     both
    0.87
     vooral
    0.86
    िटी
    0.85
     जहां
    0.84
    explique
    0.83
    케
    0.82
    Activations Density 0.031%

    No Known Activations