© 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. 58955
    Prev
    Next
    INDEX
    Explanations

    celebrity 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
     Forscher
    -0.76
    шал
    -0.66
     tie
    -0.63
    錶
    -0.63
    Easter
    -0.63
     Nieren
    -0.63
     wife
    -0.63
     executed
    -0.62
    ばら
    -0.62
    ffie
    -0.60
    POSITIVE LOGITS
     Lindsay
    1.33
     Lohan
    1.08
    Lindsay
    1.05
    fortun
    0.97
     Paris
    0.94
     heiress
    0.93
     Hilton
    0.92
    Paris
    0.90
     EBITDA
    0.88
    indsay
    0.88
    Activations Density 0.013%

    No Known Activations