© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 1733
    Prev
    Next
    INDEX
    Explanations

    occupied Palestinians

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

    medical neglect naval mines safety laws

    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
     बिज़नेस
    0.61
     thoughtfully
    0.59
     মাননীয়
    0.57
    த்தினை
    0.57
    ޢ
    0.57
    并且
    0.55
    ೦
    0.55
    ௦
    0.55
     गाँधी
    0.54
    ँव
    0.53
    POSITIVE LOGITS
     amid
    0.73
     ওই
    0.63
     yüzde
    0.61
     tantamount
    0.58
    Amid
    0.57
     lawmaker
    0.57
     bloc
    0.56
     staffers
    0.55
     bourse
    0.55
     yakni
    0.55
    Activations Density 0.174%

    No Known Activations