© 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. 72137
    Prev
    Next
    INDEX
    Explanations

    campground, campsite, Jody, BIO, Capricorn, CBT

    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
    罍
    -2.77
    敉
    -2.69
    i
    -2.69
    "
    -2.66
    will
    -2.61
     miſ
    -2.48
    
    -2.41
     enquanto
    -2.22
    硨
    -2.22
    熜
    -2.19
    POSITIVE LOGITS
    ↵↵
    2.58
     Главная
    2.48
    瀟
    2.41
    。“
    2.27
    }$.
    2.20
    الحي
    2.19
    醂
    2.16
    Bety
    2.14
     Entste
    2.11
     Gedanke
    2.06
    Activations Density 0.005%

    No Known Activations