© 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. 86894
    Prev
    Next
    INDEX
    Explanations

    Gilmore Girls

    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
    Dass
    -0.77
     serata
    -0.77
    Tucson
    -0.74
    cauciones
    -0.71
     Aktion
    -0.71
     Pediat
    -0.69
    "]);
    
    -0.69
    Tamp
    -0.68
    рез
    -0.68
     PERT
    -0.67
    POSITIVE LOGITS
     Gilmore
    1.65
    Gil
    1.30
     Rory
    1.25
     Lore
    0.95
    LORE
    0.93
    Rory
    0.91
    Retry
    0.88
     Yale
    0.81
     GG
    0.80
    ською
    0.79
    Activations Density 0.038%

    No Known Activations