© 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. 10694
    Prev
    Next
    INDEX
    Explanations

    surface properties and attributes

    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
     Our
    -1.83
    ти
    -1.73
     they
    -1.64
     จะ
    -1.60
    ></
    -1.58
     We
    -1.58
    把我
    -1.51
     スタート
    -1.48
    难以
    -1.48
    从来没有
    -1.48
    POSITIVE LOGITS
    ஂ
    2.09
    　　*
    1.98
    几种
    1.92
     nuanced
    1.90
     intricacies
    1.87
    各式
    1.73
    ︲
    1.73
     coveted
    1.73
    iembre
    1.72
     sowohl
    1.72
    Activations Density 0.039%

    No Known Activations