© 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. 17562
    Prev
    Next
    INDEX
    Explanations

    technical library names

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

    tech services and databases

    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
    淬
    0.46
    邨
    0.45
    ৌম
    0.43
    清潔
    0.43
    સિંહ
    0.43
     dechlorination
    0.42
    yatiti
    0.42
    培育
    0.41
    র্ষি
    0.41
    電荷
    0.41
    POSITIVE LOGITS
     ![
    0.51
     Product
    0.49
     GraphQL
    0.48
     "
    0.47
     HTML
    0.46
     «
    0.46
     OAuth
    0.46
     '
    0.45
     `
    0.45
     Person
    0.45
    Activations Density 0.015%

    No Known Activations