© 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. 81278
    Prev
    Next
    INDEX
    Explanations

    currency, large numbers, and mixed languages

    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
     demanda
    -0.82
     об
    -0.82
    ("%.
    -0.70
    電力
    -0.68
     aziende
    -0.68
    íncipe
    -0.67
     Volunteer
    -0.67
     özel
    -0.67
     politica
    -0.67
     化粧
    -0.66
    POSITIVE LOGITS
     millions
    0.85
     trillion
    0.83
     Rp
    0.83
     billions
    0.82
    ществ
    0.82
    uttaa
    0.80
    millions
    0.79
     ביצ
    0.77
     thousands
    0.76
    搐
    0.76
    Activations Density 0.008%

    No Known Activations