© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 90046
    Prev
    Next
    INDEX
    Explanations

    posts and microposts

    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
     Gmail
    -0.96
     iTunes
    -0.83
     عنها
    -0.82
     gmail
    -0.81
     ratings
    -0.79
     rating
    -0.79
     Seating
    -0.79
    abot
    -0.78
     쓰
    -0.77
     bookcase
    -0.76
    POSITIVE LOGITS
    post
    1.11
     caption
    1.06
     posts
    1.05
    caption
    1.05
    Post
    0.97
    relationship
    0.94
    posts
    0.93
     Comments
    0.93
    postData
    0.90
     posti
    0.89
    Activations Density 0.002%

    No Known Activations