© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 2627
    Prev
    Next
    INDEX
    Explanations

    who followed by verb

    np_acts-logits-general · gemini-2.5-flash-lite

    thoroughly/completely

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     calamity
    0.58
     disaster
    0.58
    災害
    0.56
     Disaster
    0.54
     Cal
    0.52
     calam
    0.52
     disasters
    0.51
    灾
    0.50
     आपदा
    0.49
     caliper
    0.48
    POSITIVE LOGITS
     thoroughly
    0.57
     Thorough
    0.45
     enjoys
    0.44
    olls
    0.42
    Dart
    0.39
    Manchester
    0.39
    Matrices
    0.39
    ﮗ
    0.38
     attends
    0.38
     obstruct
    0.38
    Activations Density 0.000%

    No Known Activations