© 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. 10-GEMMASCOPE-RES-131K
    7. 68671
    Prev
    Next
    INDEX
    Explanations

    ability or inability

    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
    Makan
    -1.79
    Siamo
    -1.65
     tasche
    -1.63
    Bahkan
    -1.63
    Anche
    -1.63
    Makanan
    -1.61
     使い方
    -1.61
    Минусы
    -1.61
    웹
    -1.56
     myös
    -1.55
    POSITIVE LOGITS
     one
    1.63
    ↵↵
    1.63
     WITH
    1.55
     avec
    1.49
        
    1.48
    <sup>
    1.42
    形
    1.42
    <h3>
    1.39
    ldots
    1.35
    f
    1.35
    Activations Density 0.019%

    No Known Activations