© 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. 72222
    Prev
    Next
    INDEX
    Explanations

    blatant or obvious wrongdoing

    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
    {
    -1.70
    ском
    -1.58
    ре
    -1.52
     onze
    -1.52
    /−
    -1.50
     thrive
    -1.48
    .
    -1.45
     mené
    -1.43
     вектор
    -1.42
     eradicate
    -1.41
    POSITIVE LOGITS
    1
    1.95
    iſter
    1.80
    Beispiel
    1.71
     geschlagen
    1.63
     neues
    1.60
    Ꮞ
    1.55
    栳
    1.55
     bazı
    1.55
    が少ない
    1.54
    
    1.51
    Activations Density 0.014%

    No Known Activations