© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 60875
    Prev
    Next
    INDEX
    Explanations

    pluralizing words

    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
    達は
    -0.94
    ونت
    -0.87
     Totals
    -0.85
     horas
    -0.84
     Concentrations
    -0.83
    達が
    -0.82
     darah
    -0.76
     filas
    -0.76
    ={},
    -0.75
     vivas
    -0.75
    POSITIVE LOGITS
    們
    1.38
    들
    1.37
    们
    1.16
    ों
    0.96
    々
    0.89
    ים
    0.87
    breakpoint
    0.87
    ات
    0.85
     которые
    0.85
    isOn
    0.84
    Activations Density 0.036%

    No Known Activations