© 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. 79426
    Prev
    Next
    INDEX
    Explanations

    easy to clean

    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
     Empieza
    -0.85
    ámicas
    -0.84
    vă
    -0.76
     recién
    -0.75
     usados
    -0.74
    蟆
    -0.73
     Кубка
    -0.73
     consumes
    -0.72
     rupees
    -0.71
     ранее
    -0.71
    POSITIVE LOGITS
     easy
    1.71
     wipe
    1.55
     simply
    1.51
    Easy
    1.41
     easily
    1.32
     Easy
    1.30
    easy
    1.28
     fácil
    1.21
     Simply
    1.19
    Wipe
    1.19
    Activations Density 0.010%

    No Known Activations