© 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. 2366
    Prev
    Next
    INDEX
    Explanations

    by the expert

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

    Fill opacity

    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
    тельное
    0.43
    สงค์
    0.42
    两次
    0.40
     antiguo
    0.40
     cũ
    0.39
    ̦
    0.39
    ⴽ
    0.39
    RESPONSE
    0.39
    ｿ
    0.39
    ваты
    0.38
    POSITIVE LOGITS
     Top
    0.90
     Numer
    0.86
     top
    0.81
     verified
    0.80
     educators
    0.80
    top
    0.80
    verified
    0.79
    Top
    0.78
     TOP
    0.77
    Numer
    0.77
    Activations Density 0.000%

    No Known Activations