© 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. 84628
    Prev
    Next
    INDEX
    Explanations

    urban planning and design

    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
     پیم
    -0.82
    Estilo
    -0.77
     обратиться
    -0.76
    Rend
    -0.76
    ịp
    -0.76
     Visual
    -0.75
     Panel
    -0.74
    زالة
    -0.73
     Render
    -0.73
     стиле
    -0.73
    POSITIVE LOGITS
     proposal
    1.08
     programmatic
    1.02
     strategy
    1.02
     typo
    0.99
     poche
    0.98
     intervention
    0.96
     strategies
    0.96
     condition
    0.95
    typo
    0.93
     interventions
    0.91
    Activations Density 0.022%

    No Known Activations