© 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. 7233
    Prev
    Next
    INDEX
    Explanations

    marketing, pr, social media, names, creative solutions

    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
     PR
    -2.08
    Pris
    -1.97
     Pris
    -1.95
     Priscilla
    -1.95
     prism
    -1.90
     Preston
    -1.83
    PR
    -1.79
     Prism
    -1.75
     Pratt
    -1.73
     pria
    -1.67
    POSITIVE LOGITS
    捞
    0.96
     hukuman
    0.82
    パ
    0.81
    感情
    0.75
    ที่สุด
    0.75
    TRC
    0.73
    众
    0.73
    方的
    0.72
    push
    0.72
     política
    0.70
    Activations Density 0.048%

    No Known Activations