© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 11000
    Prev
    Next
    INDEX
    Explanations

    my, a, the + noun

    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
     zui
    -1.42
     Μ
    -1.38
     andere
    -1.37
     sempre
    -1.37
     المزيد
    -1.34
     fachada
    -1.33
    지
    -1.30
    FLICT
    -1.24
     vader
    -1.23
     alho
    -1.22
    POSITIVE LOGITS
    Numerous
    1.56
     what
    1.55
     Since
    1.42
     contemplated
    1.39
     Numerous
    1.38
    ubernur
    1.37
     numerosas
    1.36
     Without
    1.34
     used
    1.30
    元に
    1.29
    Activations Density 0.839%

    No Known Activations