© 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. 98655
    Prev
    Next
    INDEX
    Explanations

    Russian and English verbs

    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
     each
    -1.24
     również
    -1.21
     присут
    -1.18
     acuerdo
    -1.16
     каждый
    -1.14
    独自
    -1.13
    Pablo
    -1.10
    我们的
    -1.10
    Each
    -1.09
     our
    -1.09
    POSITIVE LOGITS
     Româ
    1.54
     by
    1.54
     eeuw
    1.44
     Potential
    1.38
     pittore
    1.33
     Hause
    1.30
     machen
    1.30
     Heute
    1.30
     født
    1.29
     menggel
    1.27
    Activations Density 0.013%

    No Known Activations