© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 127501
    Prev
    Next
    INDEX
    Explanations

    concerning topics or clarifications

    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
    Negative Logits
     creadores
    -2.50
    سبة
    -2.42
    一個
    -2.39
    Londres
    -2.38
     expanse
    -2.38
     prosjek
    -2.34
     ขาว
    -2.34
     帅气
    -2.30
     tatuajes
    -2.28
    ssons
    -2.28
    POSITIVE LOGITS
    </em>
    3.92
     It
    3.48
    m
    3.39
    <em>
    3.05
    </h2>
    2.89
     Then
    2.75
     Also
    2.67
     verschied
    2.64
    }{
    2.61
     }
    2.53
    Activations Density 0.005%

    No Known Activations