© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39250
    Prev
    Next
    INDEX
    Explanations

    ridiculous, disgraceful, failure

    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
    熥
    -1.77
    ︲
    -1.67
     rám
    -1.61
    tización
    -1.59
     dát
    -1.55
     spécifiques
    -1.55
     tých
    -1.52
     ľudí
    -1.51
     ۱۵
    -1.48
    pří
    -1.48
    POSITIVE LOGITS
     it
    1.66
     there
    1.49
     focusing
    1.41
     this
    1.41
     promoting
    1.30
     while
    1.29
     mencegah
    1.27
     if
    1.27
     showing
    1.27
     most
    1.24
    Activations Density 0.026%

    No Known Activations