© 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. 72008
    Prev
    Next
    INDEX
    Explanations

    obeying rules

    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
    Not in Any Lists

    No Comments

    Negative Logits
     different
    -1.40
     diferentes
    -1.34
     justifyContent
    -1.27
     khác
    -1.20
    cobs
    -1.18
    datable
    -1.16
     συγ
    -1.16
    不同的
    -1.16
     Then
    -1.12
     concern
    -1.12
    POSITIVE LOGITS
     łóż
    1.18
     godziny
    1.13
    偶尔
    1.09
     creado
    1.09
     マルチ
    1.09
     Announces
    1.08
     doporu
    1.06
     प्रदान
    1.03
     advises
    1.02
    NECTIONS
    1.01
    Activations Density 0.074%

    No Known Activations