© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10670
    Prev
    Next
    INDEX
    Explanations

    Dicamba, msdatasource, build

    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
     τὸν
    -1.61
     convient
    -1.57
     hini
    -1.53
     kulak
    -1.52
     فقط
    -1.52
     этой
    -1.49
     timmar
    -1.48
     τὴν
    -1.48
     mecánica
    -1.47
     gestartet
    -1.46
    POSITIVE LOGITS
     in
    1.96
    院校
    1.57
    A
    1.52
    мл
    1.51
     По
    1.48
    in
    1.48
     with
    1.47
     has
    1.44
     кроссовки
    1.44
     but
    1.43
    Activations Density 0.001%

    No Known Activations