© 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. 56786
    Prev
    Next
    INDEX
    Explanations

    word or linguistic unit

    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
     Aru
    -0.79
     hoort
    -0.79
     NUKAT
    -0.77
     lesión
    -0.75
     verkau
    -0.74
     fuckin
    -0.73
    iniques
    -0.73
    büro
    -0.72
    Morte
    -0.72
     zoeken
    -0.71
    POSITIVE LOGITS
     word
    3.05
    word
    1.99
     palabra
    1.79
     слово
    1.71
    Word
    1.52
     palavra
    1.49
     F
    1.46
     dreaded
    1.41
     parola
    1.41
    WORD
    1.40
    Activations Density 0.032%

    No Known Activations