© 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. 34-GEMMASCOPE-RES-131K
    7. 7037
    Prev
    Next
    INDEX
    Explanations

    localization and localized terms

    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_34/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
    clearInterval
    -0.75
    Smack
    -0.75
    Configura
    -0.71
     ditangkap
    -0.71
     boş
    -0.68
    getCache
    -0.68
    ليك
    -0.68
     jaj
    -0.67
     Sver
    -0.67
    רק
    -0.66
    POSITIVE LOGITS
     localization
    2.95
     localized
    2.86
     localize
    2.64
     localisation
    2.59
    localized
    2.44
     Localization
    2.42
     localised
    2.39
     Localized
    2.39
    Localization
    2.33
    localization
    2.25
    Activations Density 0.098%

    No Known Activations