© 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. 98490
    Prev
    Next
    INDEX
    Explanations

    motoring tickets and fines

    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
     Perkin
    -0.92
    utados
    -0.86
     marketing
    -0.80
    bau
    -0.79
     poisoning
    -0.77
     tartalomajánló
    -0.77
     الطب
    -0.76
    汌
    -0.76
     interesados
    -0.75
    mbolic
    -0.75
    POSITIVE LOGITS
     tickets
    2.17
     ticket
    2.06
    ticket
    1.74
    Tickets
    1.68
    tickets
    1.65
    Ticket
    1.63
     Tickets
    1.63
     Ticket
    1.59
     citations
    1.52
     fines
    1.48
    Activations Density 0.021%

    No Known Activations