© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3513
    Prev
    Next
    INDEX
    Explanations

    Reduced gradient, prime factors, invention

    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
    Negative Logits
    冷凍
    -0.77
    庁
    -0.75
    úrese
    -0.75
    ỏ
    -0.75
     мне
    -0.74
     彈
    -0.73
    ⬤
    -0.72
     nära
    -0.70
    езд
    -0.70
    克拉
    -0.69
    POSITIVE LOGITS
     pn
    0.89
     hydroly
    0.78
    PLAN
    0.76
    ≌
    0.76
    pnt
    0.74
    левая
    0.74
     insensitive
    0.74
    จำนวน
    0.74
    Sustainability
    0.74
    thal
    0.74
    Activations Density 0.008%

    No Known Activations