© 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. 97826
    Prev
    Next
    INDEX
    Explanations

    escape from jail

    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
     насеље
    -0.88
     réponses
    -0.79
     Pronto
    -0.78
    
    -0.78
     Monark
    -0.78
    イツ
    -0.77
     commencent
    -0.76
    罴
    -0.76
     tsy
    -0.76
     Laramie
    -0.76
    POSITIVE LOGITS
     escape
    4.69
     escaped
    4.03
     escapes
    3.94
    escape
    3.80
     Escape
    3.50
     escaping
    3.50
    Escape
    3.25
    ESCAPE
    2.73
     ESCAPE
    2.69
    escaped
    2.66
    Activations Density 0.025%

    No Known Activations