© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 34799
    Prev
    Next
    INDEX
    Explanations

    states and cities

    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
     mangá
    -0.77
     gameOver
    -0.74
     javas
    -0.73
     noticia
    -0.73
    duga
    -0.73
     rapat
    -0.72
     Quelques
    -0.71
    🚒
    -0.70
     blueberries
    -0.70
     musée
    -0.69
    POSITIVE LOGITS
     State
    3.61
     state
    3.33
    State
    2.81
    state
    2.55
     STATE
    2.17
    STATE
    1.91
     estado
    1.66
     राज्य
    1.59
     States
    1.52
     states
    1.52
    Activations Density 0.045%

    No Known Activations