© 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. 2010
    Prev
    Next
    INDEX
    Explanations

    URL status and services

    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
    heids
    0.48
    iments
    0.41
    साद
    0.39
     Controvers
    0.38
    lige
    0.38
    ধান
    0.38
     Ware
    0.38
    闸
    0.38
    ló
    0.37
     Dore
    0.37
    POSITIVE LOGITS
     url
    1.84
    url
    1.72
     URL
    1.70
     Url
    1.65
    URL
    1.60
    Url
    1.53
     urls
    1.48
     URLs
    1.43
    urls
    1.33
    getUrl
    1.32
    Activations Density 0.050%

    No Known Activations