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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9683
    Prev
    Next
    INDEX
    Explanations

    social media sharing and outreach

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

    crowd distributed development

    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_40_width_16k_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
     ২০২৩
    0.99
     ২০২২
    0.96
    🫶
    0.91
    🫣
    0.90
    🩷
    0.89
    🥵
    0.88
    🥰
    0.86
     २०२
    0.86
    🤍
    0.84
    🥺
    0.83
    POSITIVE LOGITS
     Twitter
    1.14
     twitter
    1.09
    Twitter
    1.06
     tweeted
    1.05
     Flickr
    1.05
     Tweets
    1.03
    Tweet
    1.02
     tweeting
    1.02
     crowds
    1.02
     Tweet
    1.02
    Activations Density 1.446%

    No Known Activations