© 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. 34-GEMMASCOPE-RES-131K
    7. 47286
    Prev
    Next
    INDEX
    Explanations

    Viz, Miz, Siz, Biz, IZ

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     contd
    -0.79
    يته
    -0.79
    ⃘
    -0.77
     bénéfic
    -0.77
    ederos
    -0.74
    ását
    -0.73
     stit
    -0.72
    priate
    -0.72
     wtf
    -0.71
     metà
    -0.71
    POSITIVE LOGITS
     chữa
    0.79
    zes
    0.77
    PreferredItem
    0.77
    ವ
    0.77
     gaze
    0.77
     Photos
    0.76
    aaa
    0.73
    aa
    0.73
    zo
    0.72
    itens
    0.72
    Activations Density 0.028%

    No Known Activations