© 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. 34-GEMMASCOPE-RES-131K
    7. 49697
    Prev
    Next
    INDEX
    Explanations

    method/function calls

    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_34/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
    owohl
    -0.80
    AMENT
    -0.79
    avení
    -0.78
    фри
    -0.75
    Bend
    -0.73
    mands
    -0.71
     Works
    -0.71
     Работа
    -0.71
    Tucker
    -0.71
     pierde
    -0.70
    POSITIVE LOGITS
     method
    4.19
     function
    3.86
    函数
    3.39
     methods
    3.30
    方法
    3.17
    method
    2.80
     Method
    2.72
    function
    2.69
     functions
    2.66
    Method
    2.64
    Activations Density 0.375%

    No Known Activations