© 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. 11140
    Prev
    Next
    INDEX
    Explanations

    Japanese numbers and "again"

    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
     dança
    -0.99
     koltuk
    -0.98
     borracha
    -0.92
    Ảnh
    -0.92
     zapis
    -0.91
    気がします
    -0.91
     Οι
    -0.91
    beros
    -0.91
     Ostat
    -0.90
    に来て
    -0.89
    POSITIVE LOGITS
     again
    1.13
    框架
    0.98
    も
    0.97
    ですが
    0.95
    が
    0.94
     also
    0.93
    に
    0.92
    again
    0.92
    で
    0.90
    nadequate
    0.89
    Activations Density 0.001%

    No Known Activations