© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128206
    Prev
    Next
    INDEX
    Explanations

    abbreviation followed by specific word/symbol

    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
     jūs
    -1.06
     darbu
    -0.95
     What
    -0.94
     sucht
    -0.93
     darbo
    -0.93
    ìm
    -0.90
     so
    -0.89
    dreamstime
    -0.88
     There
    -0.87
    ологи
    -0.85
    POSITIVE LOGITS
    になれば
    1.05
    為に
    1.04
    になったら
    1.00
    わたし
    1.00
     WISCONSIN
    0.99
    lograph
    0.96
    的表现
    0.96
    ツイッター
    0.96
     Vinh
    0.94
     Batavia
    0.93
    Activations Density 0.000%

    No Known Activations