© 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. 91001
    Prev
    Next
    INDEX
    Explanations

    escape from or escape code

    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
     tempi
    -0.94
     guer
    -0.84
     suivant
    -0.84
     sexe
    -0.82
    IGHTS
    -0.81
     marginBottom
    -0.81
    agi
    -0.81
     ribu
    -0.80
    uaian
    -0.80
    我们要
    -0.79
    POSITIVE LOGITS
     Escape
    1.40
    goat
    1.28
     route
    1.28
     hatch
    1.14
     escape
    1.13
     Es
    1.13
     escap
    1.11
    Escape
    1.09
     escapes
    1.08
     mechanism
    1.06
    Activations Density 0.017%

    No Known Activations