© 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. 38264
    Prev
    Next
    INDEX
    Explanations

    arrest and related legal actions

    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
    axiom
    -0.80
    Safari
    -0.79
     Majesté
    -0.74
    ómago
    -0.73
     (†
    -0.73
    ATP
    -0.73
     Safari
    -0.72
    bonsoir
    -0.71
    ReactDOM
    -0.69
     منها
    -0.69
    POSITIVE LOGITS
     arrest
    6.13
     arrested
    5.88
     arrests
    5.38
    arrest
    4.38
     Arrest
    4.22
     arresting
    4.00
    Arrest
    3.98
     Arrested
    3.47
    逮捕
    3.09
     arre
    2.67
    Activations Density 0.112%

    No Known Activations