Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8167
    Prev
    Next
    INDEX
    Explanations

    twitter bootstrap

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    s
    -1.26
    IS
    -1.02
     тех
    -0.95
    çoivent
    -0.89
     完了
    -0.88
    AT
    -0.88
    !’
    -0.87
     красивый
    -0.86
    として
    -0.86
    ?"
    -0.86
    POSITIVE LOGITS
     Twitter
    1.37
     twitter
    1.30
    twitter
    1.20
    🐦
    1.11
     tweeting
    1.08
     Tweet
    1.07
    sphere
    1.05
     Tweets
    1.05
     Twe
    1.01
     twit
    1.01
    Activations Density 0.008%

    No Known Activations