© 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. 22-GEMMASCOPE-RES-131K
    7. 68439
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    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_22/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
    othes
    -1.05
     vidi
    -1.02
     lanterna
    -1.00
    アレルギー
    -1.00
    caping
    -0.99
    crats
    -0.99
    istics
    -0.99
     cartaz
    -0.95
    phans
    -0.95
    ($)
    -0.94
    POSITIVE LOGITS
    ımıza
    1.06
     Теперь
    1.01
     their
    0.95
     which
    0.95
     amables
    0.94
     cómodo
    0.91
     Луч
    0.91
    Bi
    0.90
     Фото
    0.89
    やか
    0.86
    Activations Density 0.002%

    No Known Activations