© 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. 62500
    Prev
    Next
    INDEX
    Explanations

    competition, conflict, or comparison

    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
    及び
    -1.36
     дори
    -1.23
     salvación
    -1.19
     квіт
    -1.17
    又被
    -1.14
    ffiti
    -1.12
     удачи
    -1.10
    搅拌
    -1.09
    などなど
    -1.09
     of
    -1.09
    POSITIVE LOGITS
     versus
    1.36
     vs
    1.29
    Interestingly
    1.25
    🛡
    1.19
     pensent
    1.17
    )−
    1.15
     menangis
    1.15
    𖣘
    1.14
    🗣
    1.13
     inconnu
    1.13
    Activations Density 0.061%

    No Known Activations