© 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. 489
    Prev
    Next
    INDEX
    Explanations

    java @Override annotation

    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
    тся
    -0.91
    扼
    -0.86
     estuviera
    -0.79
     crime
    -0.79
    …~
    -0.77
     erat
    -0.75
    ܬ
    -0.75
    殷
    -0.75
     umumnya
    -0.74
     mitsubishi
    -0.73
    POSITIVE LOGITS
     която
    0.88
    логу
    0.76
    来的
    0.76
    (':
    0.75
    getOrder
    0.74
    让他们
    0.74
    Het
    0.73
    rozco
    0.73
     آنان
    0.72
    ϭ
    0.72
    Activations Density 0.002%

    No Known Activations