Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7700
    Prev
    Next
    INDEX
    Explanations

    deaths of famous people

    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
    dst
    -0.81
     Central
    -0.75
     decy
    -0.70
     cellar
    -0.70
    ig
    -0.66
    瘸
    -0.66
    decrease
    -0.65
    擒
    -0.65
     exp
    -0.65
     infierno
    -0.65
    POSITIVE LOGITS
     died
    1.27
     Kobe
    1.22
    Kobe
    1.20
     Chadwick
    1.05
     (†
    1.00
     deaths
    0.98
     décès
    0.96
     Irr
    0.95
    Décès
    0.88
    MCA
    0.85
    Activations Density 0.051%

    No Known Activations