© 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. 6852
    Prev
    Next
    INDEX
    Explanations

    beginning of phrases and questions

    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
     dengan
    -2.92
     Usually
    -2.53
    ～！
    -2.34
     Belakang
    -2.31
     Generally
    -2.31
     Certainly
    -2.28
     wisata
    -2.28
    〜！
    -2.28
    们的
    -2.25
     Without
    -2.22
    POSITIVE LOGITS
    }
    2.73
     spearheaded
    2.61
    
    2.58
    и
    2.53
    '
    2.52
     magnificent
    2.50
    ⮑
    2.48
    蹀
    2.44
     molti
    2.39
     acclaimed
    2.36
    Activations Density 0.000%

    No Known Activations