© 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. 92577
    Prev
    Next
    INDEX
    Explanations

    last name or surname

    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
     given
    -0.79
     remuner
    -0.78
     Ado
    -0.76
    λε
    -0.74
    ждения
    -0.74
    bulaire
    -0.74
     Nickelodeon
    -0.71
    ል
    -0.70
     Yourself
    -0.69
     interpolate
    -0.69
    POSITIVE LOGITS
     surname
    2.56
     last
    2.38
    LastName
    2.02
     lastName
    1.91
    lastName
    1.91
    surname
    1.91
    lastname
    1.91
     фами
    1.75
    Last
    1.74
     surnames
    1.70
    Activations Density 0.029%

    No Known Activations