© 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. 108059
    Prev
    Next
    INDEX
    Explanations

    typical impulse, four busted

    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
    莞
    -0.92
     величи
    -0.85
     прекра
    -0.82
     Pilihan
    -0.82
    нон
    -0.82
     yaka
    -0.81
     来自
    -0.81
    podes
    -0.81
     bibit
    -0.80
     I
    -0.80
    POSITIVE LOGITS
     ht
    1.04
    ཎ
    1.03
    ཊ
    1.01
     гита
    0.93
     Gebet
    0.92
    [])
    0.91
     neut
    0.89
     Seuss
    0.89
    lamda
    0.89
     juntamente
    0.88
    Activations Density 0.008%

    No Known Activations