© 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. 34-GEMMASCOPE-RES-131K
    4. 84013
    Prev
    Next
    INDEX
    Explanations

    words starting with catal

    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
    Schriften
    -0.77
     برگزار
    -0.77
    că
    -0.72
    кви
    -0.71
    studie
    -0.70
    wegs
    -0.69
     Hamlin
    -0.69
     Tulane
    -0.68
    calling
    -0.68
     ensemble
    -0.68
    POSITIVE LOGITS
     katal
    0.86
     catal
    0.85
     Catal
    0.79
    身に
    0.76
     Dressing
    0.75
     converters
    0.74
    Catal
    0.74
    殘
    0.73
    改进
    0.73
     хочу
    0.73
    Activations Density 0.034%

    No Known Activations