© 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. 89943
    Prev
    Next
    INDEX
    Explanations

    actress names

    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
     masculinity
    -1.04
    mascul
    -0.97
     handsome
    -0.93
    INR
    -0.85
    }}%
    -0.82
     masculine
    -0.81
     himself
    -0.80
    ẩu
    -0.78
     ragazze
    -0.78
    ชาย
    -0.77
    POSITIVE LOGITS
     actress
    1.00
    Actress
    0.92
     Actress
    0.80
     त
    0.79
    女優
    0.78
    есть
    0.78
    INTRODUCTION
    0.77
    actress
    0.77
     actriz
    0.75
    DOUBLE
    0.71
    Activations Density 0.084%

    No Known Activations