© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38718
    Prev
    Next
    INDEX
    Explanations

    method retrieval

    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
     {
    -1.77
    黑衣
    -1.68
     layui
    -1.63
    hauled
    -1.51
     }}$
    -1.50
     дали
    -1.48
    鹇
    -1.46
     parachoque
    -1.44
    謦
    -1.43
    i
    -1.41
    POSITIVE LOGITS
    ↵↵
    1.71
     innych
    1.64
     Anyway
    1.56
     striking
    1.52
     erwähnten
    1.50
     tuviera
    1.44
     You
    1.44
     vorhandenen
    1.41
     If
    1.40
     besonderen
    1.39
    Activations Density 0.011%

    No Known Activations