© 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. 29918
    Prev
    Next
    INDEX
    Explanations

    codes and technical terms

    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
     informed
    -0.79
    DDL
    -0.74
    サラ
    -0.74
    iremos
    -0.73
     Stomp
    -0.72
     think
    -0.71
    %?
    -0.68
     bae
    -0.68
     lomb
    -0.67
    CCR
    -0.65
    POSITIVE LOGITS
     sezonu
    0.89
     шапка
    0.84
     balkon
    0.83
    hig
    0.82
    profiles
    0.82
    chaqueta
    0.82
     adresu
    0.81
     AssemblyCulture
    0.81
     exacte
    0.81
    Nuorodos
    0.79
    Activations Density 0.002%

    No Known Activations