© 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. 47096
    Prev
    Next
    INDEX
    Explanations

    sentence comprehension

    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
    颍
    -0.80
     asset
    -0.79
     chers
    -0.78
     تضيفلها
    -0.76
     terrified
    -0.75
     جلس
    -0.74
    retario
    -0.73
     Bluff
    -0.73
    shar
    -0.72
     Ghar
    -0.71
    POSITIVE LOGITS
    garden
    0.82
     comprehension
    0.82
    Sentence
    0.79
     sentence
    0.79
     berühm
    0.77
     comprehended
    0.77
     predictability
    0.76
    MemberId
    0.75
     reading
    0.75
     Sentence
    0.74
    Activations Density 0.070%

    No Known Activations