© 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. 59918
    Prev
    Next
    INDEX
    Explanations

    City, Middletown, Orange, Brenda Forbes

    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
    分手
    -0.77
     empf
    -0.73
    Moon
    -0.72
     Burma
    -0.72
     Massen
    -0.71
    示例
    -0.69
    arrer
    -0.69
    Cloud
    -0.68
    JsonNode
    -0.68
    зирован
    -0.67
    POSITIVE LOGITS
     Middletown
    0.90
     Orange
    0.84
     DET
    0.81
    dut
    0.80
     ORANGE
    0.78
    ORANGE
    0.77
    Belf
    0.75
    pezi
    0.75
    rógeno
    0.73
    Nye
    0.73
    Activations Density 0.025%

    No Known Activations