© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3084
    Prev
    Next
    INDEX
    Explanations

    Finnish, customers, service

    np_acts-logits-general · gemini-2.5-flash-lite

    prohibiting harmful content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rostrum
    0.44
     उपनिवेश
    0.43
    computed
    0.42
     anzi
    0.40
    貧
    0.39
    captive
    0.39
    ንስ
    0.39
     нередко
    0.39
    讽
    0.38
    contrast
    0.38
    POSITIVE LOGITS
     고객
    0.59
     Oy
    0.56
     możesz
    0.56
     kunder
    0.54
     Kunden
    0.52
     Finnish
    0.51
     serviced
    0.51
     yhte
    0.51
     обслуживание
    0.51
    lom
    0.51
    Activations Density 0.001%

    No Known Activations