© 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. 38555
    Prev
    Next
    INDEX
    Explanations

    being safe

    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
    
    -1.75
    ugeot
    -1.66
     karte
    -1.64
    茈
    -1.64
     idr
    -1.63
    螄
    -1.63
    PARATION
    -1.58
     ferie
    -1.54
    tamaris
    -1.53
     vna
    -1.52
    POSITIVE LOGITS
     safe
    1.84
     haven
    1.77
    A
    1.66
     Isn
    1.60
    大约
    1.58
     secure
    1.55
     otras
    1.55
    Many
    1.51
     h
    1.51
    at
    1.50
    Activations Density 0.030%

    No Known Activations