© 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. 25760
    Prev
    Next
    INDEX
    Explanations

    illegal activities and crime

    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
     casket
    -0.88
     booze
    -0.85
     khuy
    -0.78
     Fitted
    -0.77
     SATURDAY
    -0.76
     Edizioni
    -0.75
     réussite
    -0.74
     Pis
    -0.74
     häls
    -0.74
    -^
    -0.73
    POSITIVE LOGITS
     case
    1.21
     criminal
    1.02
     Case
    1.00
     illegal
    0.99
     Criminal
    0.97
    Case
    0.93
     involved
    0.91
     police
    0.91
     cases
    0.88
    WebControls
    0.88
    Activations Density 0.014%

    No Known Activations