© 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. 11736
    Prev
    Next
    INDEX
    Explanations

    language placeholders and multilingual terms

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

    variable or function names related to translation and internationalization (i18n) in code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     also
    -2.05
     for
    -1.58
     because
    -1.57
     It
    -1.55
     For
    -1.54
    一个小
    -1.52
     Also
    -1.40
     The
    -1.38
     That
    -1.38
    也非常
    -1.36
    POSITIVE LOGITS
    probieren
    1.68
     passende
    1.63
    kehren
    1.56
     Sénat
    1.49
    
    1.48
    RTLD
    1.45
     horaires
    1.45
    uteurs
    1.44
     séjours
    1.44
     Privacidad
    1.38
    Activations Density 0.009%

    No Known Activations