© 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. 29905
    Prev
    Next
    INDEX
    Explanations

    code generation prompts

    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
    
    -1.29
     Sør
    -1.22
     unſ
    -1.18
    ῖν
    -1.15
     Dokter
    -1.15
     także
    -1.13
     também
    -1.13
     също
    -1.12
     również
    -1.11
    achers
    -1.10
    POSITIVE LOGITS
     möglicherweise
    1.15
     vielmehr
    1.15
     unmittelbar
    1.10
     могло
    1.09
    了一個
    1.09
     Eigentümer
    1.03
    が多く
    1.02
    ところで
    1.02
     vermutlich
    1.02
     регионе
    1.01
    Activations Density 0.112%

    No Known Activations