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. 7768
    Prev
    Next
    INDEX
    Explanations

    luck, fortunes, lucky endings

    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
    izacji
    -0.87
    댓
    -0.84
    vasive
    -0.79
    萜
    -0.79
    Ers
    -0.78
    pakatan
    -0.76
    Unavailable
    -0.75
    όρ
    -0.74
    Unique
    -0.73
    Defining
    -0.73
    POSITIVE LOGITS
     luck
    2.53
     lucky
    2.16
     Luck
    1.99
     LUCK
    1.82
     prosperity
    1.78
     unlucky
    1.78
    luck
    1.77
    Luck
    1.75
     Lucky
    1.65
    lucky
    1.64
    Activations Density 0.018%

    No Known Activations