© 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. 10-GEMMASCOPE-RES-131K
    4. 48055
    Prev
    Next
    INDEX
    Explanations

    appeal from the united states tax court

    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_10/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
     αλλά
    -2.88
    ܞ
    -2.53
     หรือ
    -2.44
    isesta
    -2.38
    0
    -2.28
    淶
    -2.25
    </h4>
    -2.20
    こともあり
    -2.16
    白的
    -2.14
    та
    -2.11
    POSITIVE LOGITS
     was
    3.03
    {
    2.83
    鸶
    2.80
     have
    2.61
     getting
    2.41
    
    2.38
     currently
    2.38
    を見て
    2.33
    B
    2.33
    P
    2.28
    Activations Density 0.027%

    No Known Activations