© 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. 10-GEMMASCOPE-RES-131K
    7. 29201
    Prev
    Next
    INDEX
    Explanations

    explaining processes

    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_10/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
     for
    -1.91
     will
    -1.81
     систе
    -1.73
     was
    -1.63
     from
    -1.60
     in
    -1.52
    鈇
    -1.49
    鑪
    -1.48
     cantora
    -1.46
    Another
    -1.45
    POSITIVE LOGITS
     you
    2.14
     巾
    1.52
    跟你
    1.49
    りましたが
    1.48
     étoient
    1.48
     brachten
    1.45
     they
    1.41
    formatics
    1.40
    まぁ
    1.39
    ности
    1.38
    Activations Density 0.051%

    No Known Activations