© 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. 119061
    Prev
    Next
    INDEX
    Explanations

    early days, years, stages

    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
     berusaha
    -1.48
     a
    -1.47
     CLAIMS
    -1.43
    rej
    -1.39
     veröffentlich
    -1.39
     prachtige
    -1.38
     bouwen
    -1.35
    ݯ
    -1.35
    不一定
    -1.35
     اصفه
    -1.34
    POSITIVE LOGITS
    Когда
    1.80
     его
    1.65
     of
    1.63
    Leírás
    1.57
     years
    1.55
     inception
    1.55
     когда
    1.44
    澳門
    1.42
     beginnings
    1.38
    Кто
    1.38
    Activations Density 0.042%

    No Known Activations