© 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. 34-GEMMASCOPE-RES-131K
    7. 78441
    Prev
    Next
    INDEX
    Explanations

    names starting with uck or similar

    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
     likewise
    -0.78
     JOS
    -0.75
     Antarctica
    -0.70
     streng
    -0.70
    یز
    -0.68
     cutlery
    -0.68
     défauts
    -0.68
    ianum
    -0.67
    tiness
    -0.66
    Въ
    -0.65
    POSITIVE LOGITS
     muncul
    0.78
    Milli
    0.73
    luxury
    0.73
     фаса
    0.70
    buying
    0.70
    不久
    0.69
    paka
    0.69
    笛
    0.68
     запас
    0.68
     immediate
    0.68
    Activations Density 0.031%

    No Known Activations