© 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. 109234
    Prev
    Next
    INDEX
    Explanations

    legal products and transactions

    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
    нечно
    -0.87
    noStroke
    -0.82
    нном
    -0.81
    ⣥
    -0.81
     ヘア
    -0.79
    عتقد
    -0.77
    芥
    -0.76
    |'='
    -0.76
    ester
    -0.75
    је
    -0.75
    POSITIVE LOGITS
     legitimate
    4.63
     lawful
    3.91
     legit
    3.70
    合法
    3.64
     legitimately
    3.41
     lawfully
    3.23
     legally
    3.03
     legal
    2.98
     legality
    2.55
    lawful
    2.52
    Activations Density 0.092%

    No Known Activations