© 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. 12555
    Prev
    Next
    INDEX
    Explanations

    code declarations and programming constructs

    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
    ivotopis
    -1.67
     и
    -1.67
     और
    -1.65
    「
    -1.55
    ۬
    -1.52
    および
    -1.47
     стиль
    -1.45
    THINK
    -1.42
     și
    -1.41
    THEN
    -1.41
    POSITIVE LOGITS
     Geräten
    1.70
    慥
    1.69
    -};
    1.59
     Situationen
    1.57
     każdej
    1.55
     każde
    1.54
     ausreich
    1.52
     arent
    1.52
     Handeln
    1.51
    ظمة
    1.50
    Activations Density 0.070%

    No Known Activations