© 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. 40041
    Prev
    Next
    INDEX
    Explanations

    event handler sender

    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
     that
    -1.38
     this
    -1.26
     more
    -1.17
     seems
    -1.16
    Seems
    -1.07
     serta
    -1.06
     menetap
    -1.06
     all
    -1.06
    ائد
    -1.04
     tiks
    -1.04
    POSITIVE LOGITS
    少なくとも
    1.07
    不仅仅
    1.05
    起码
    1.02
     prodig
    1.00
    гно
    0.99
    чехол
    0.98
     ewe
    0.96
     simil
    0.95
    或許
    0.95
    蹿
    0.94
    Activations Density 0.001%

    No Known Activations