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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 2252
    Prev
    Next
    INDEX
    Explanations

    Dean or Dek variations

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

    dek or de combinations

    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
    靂
    0.40
     NONINFRINGEMENT
    0.39
     ಉ
    0.38
    粼
    0.37
    秪
    0.37
    त्रियों
    0.37
    नोई
    0.37
    岦
    0.36
     cillum
    0.36
    螅
    0.35
    POSITIVE LOGITS
     Dean
    2.66
    Dean
    2.59
     Dek
    2.47
     dean
    2.47
     dek
    2.39
     デ
    2.33
    デ
    2.33
    Dek
    2.31
    dean
    2.31
     데
    2.28
    Activations Density 0.399%

    No Known Activations