© 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. 6716
    Prev
    Next
    INDEX
    Explanations

    additional details and instructions

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

    instructions and details

    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
     intravascular
    0.45
     জ্ঞানের
    0.43
    ள்
    0.42
    🏭
    0.40
    ಜ್ಞ
    0.40
    делить
    0.39
    識
    0.39
     aldehyde
    0.38
    profissional
    0.37
    浩
    0.37
    POSITIVE LOGITS
     dates
    1.48
     instructions
    1.33
     Dates
    1.28
     schedule
    1.26
     deadlines
    1.26
    dates
    1.25
    Dates
    1.23
     guidelines
    1.23
     FAQs
    1.22
     directions
    1.20
    Activations Density 0.348%

    No Known Activations