© 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. 10-GEMMASCOPE-RES-131K
    7. 70675
    Prev
    Next
    INDEX
    Explanations

    New York City

    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_10/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
     because
    -1.51
    她
    -1.47
    我們
    -1.44
    他們
    -1.40
    nitř
    -1.38
     people
    -1.34
    因為
    -1.33
     those
    -1.32
     that
    -1.31
     they
    -1.30
    POSITIVE LOGITS
    卨
    1.55
    鸬
    1.46
     querem
    1.43
    껏
    1.43
     disposent
    1.43
    荦
    1.42
    ())));
    1.40
     fala
    1.40
    
    1.40
    ***********/
    1.37
    Activations Density 0.298%

    No Known Activations