© 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. 127770
    Prev
    Next
    INDEX
    Explanations

    viewDidLoad method 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_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
    u
    -3.41
    ed
    -3.20
     {
    -2.77
    -2.67
    r
    -2.59
    re
    -2.53
     '
    -2.50
     :
    -2.50
    e
    -2.42
    i
    -2.31
    POSITIVE LOGITS
    沇
    3.25
    趼
    2.77
    衪
    2.69
    ){
    2.67
    蕺
    2.66
     搞笑
    2.59
    -“
    2.59
    鋮
    2.56
    偸
    2.55
    )',
    2.52
    Activations Density 0.006%

    No Known Activations