© 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. 123522
    Prev
    Next
    INDEX
    Explanations

    verbs describing states or occurrences

    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
     was
    -2.06
    pters
    -1.78
    🤭
    -1.66
     doesn
    -1.63
     can
    -1.60
     seems
    -1.59
     has
    -1.58
     been
    -1.57
     started
    -1.56
     isn
    -1.53
    POSITIVE LOGITS
    だそうです
    1.70
     다시
    1.61
    their
    1.61
    ～～～～
    1.59
     vollständ
    1.55
    ญี่ป
    1.53
     любых
    1.52
     Commonly
    1.51
    こんばん
    1.49
    と書
    1.49
    Activations Density 0.239%

    No Known Activations