© 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. 1591
    Prev
    Next
    INDEX
    Explanations

    technical components like plugin, runtime, filesystem

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

    preceding technical terms

    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
    鴛
    0.46
    廡
    0.46
    犢
    0.46
    清潔
    0.46
    鳧
    0.46
    entretien
    0.46
    綃
    0.45
    社會
    0.45
    龕
    0.45
    瀉
    0.45
    POSITIVE LOGITS
     JSON
    1.00
     default
    0.97
     metadata
    0.96
     runtime
    0.94
     filesystem
    0.94
     HTML
    0.93
     configurable
    0.92
     user
    0.91
     HTTP
    0.91
     YAML
    0.88
    Activations Density 1.139%

    No Known Activations