© 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. 22-GEMMASCOPE-RES-131K
    7. 12829
    Prev
    Next
    INDEX
    Explanations

    Maryland and Baltimore entities

    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_22/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
     gustan
    -0.94
    楽しめます
    -0.93
    wala
    -0.93
    DPS
    -0.93
    hould
    -0.91
     ıs
    -0.90
     Ramírez
    -0.90
    cito
    -0.90
    thodox
    -0.89
     toch
    -0.89
    POSITIVE LOGITS
    Maryland
    1.09
     Maryland
    1.08
     Chesapeake
    1.06
     law
    0.94
    ɢ
    0.93
     vinculado
    0.88
    八年
    0.87
    kkers
    0.87
     dieną
    0.86
     well
    0.86
    Activations Density 0.016%

    No Known Activations