© 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. 73224
    Prev
    Next
    INDEX
    Explanations

    Ler and Lorenzo names

    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
    d
    -3.48
    或者
    -3.20
     a
    -3.17
    呖
    -3.03
     {
    -3.02
     这个
    -2.89
    
    -2.78
    ஂ
    -2.72
    。“
    -2.70
    g
    -2.70
    POSITIVE LOGITS
     tne
    2.41
    妧
    2.31
     crammed
    2.28
     Geräten
    2.27
     heath
    2.22
     wła
    2.22
    闐
    2.22
     også
    2.20
    
    2.20
    嫿
    2.19
    Activations Density 0.003%

    No Known Activations