© 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. 38354
    Prev
    Next
    INDEX
    Explanations

    think that can

    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
     fortfarande
    -1.49
    čne
    -1.30
    )”.
    -1.29
    лятор
    -1.20
     också
    -1.19
     stå
    -1.19
     rospy
    -1.18
     alleen
    -1.16
    ampunk
    -1.16
     môže
    -1.16
    POSITIVE LOGITS
     other
    1.57
     same
    1.41
     others
    1.39
     ofici
    1.34
     erlä
    1.30
    句話
    1.29
     tentativo
    1.26
     rodas
    1.24
     collegamento
    1.21
    齣
    1.20
    Activations Density 0.017%

    No Known Activations