© 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. 49957
    Prev
    Next
    INDEX
    Explanations

    legal case information and dates

    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
     języka
    -0.83
    วง
    -0.81
    дэ
    -0.75
    พบ
    -0.72
     Regeln
    -0.71
     ľ
    -0.71
     Meeting
    -0.71
    ppu
    -0.69
    ец
    -0.69
    の商品
    -0.69
    POSITIVE LOGITS
    zewod
    0.82
    onBlur
    0.81
     sanitario
    0.78
     Nachbar
    0.78
    
    0.76
     IPT
    0.74
    inga
    0.74
    uc
    0.74
     Michaela
    0.73
     screamed
    0.73
    Activations Density 0.006%

    No Known Activations