© 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. 123972
    Prev
    Next
    INDEX
    Explanations

    implicit val/class

    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
    of
    -1.84
    鵙
    -1.49
    question
    -1.47
     moft
    -1.43
     firft
    -1.43
    ються
    -1.42
    oler
    -1.41
     feitas
    -1.40
     achet
    -1.36
     役
    -1.35
    POSITIVE LOGITS
    0
    1.53
    なりません
    1.44
     inaprop
    1.43
     镇
    1.41
    曏
    1.41
    咴
    1.40
     esperaba
    1.40
     أيضاً
    1.37
     Both
    1.33
    也不能
    1.30
    Activations Density 0.011%

    No Known Activations