© 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. 70446
    Prev
    Next
    INDEX
    Explanations

    version numbers and software updates

    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
     with
    -1.71
     some
    -1.62
    に行ってきました
    -1.33
    the
    -1.32
     methods
    -1.31
     one
    -1.28
    ness
    -1.28
     χρήση
    -1.27
     without
    -1.27
    얻
    -1.24
    POSITIVE LOGITS
     juſ
    1.45
     décédé
    1.43
    abilia
    1.38
    罽
    1.38
     marié
    1.33
     prêtre
    1.29
    𐄁
    1.28
     craindre
    1.27
     gracioso
    1.26
     to
    1.25
    Activations Density 0.027%

    No Known Activations