© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63641
    Prev
    Next
    INDEX
    Explanations

    content management system

    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
    Not in Any Lists

    No Comments

    Negative Logits
    searchResults
    -0.76
     rootReducer
    -0.76
    enddo
    -0.75
    ilove
    -0.74
    женной
    -0.74
     classical
    -0.73
     indivíduo
    -0.72
     perigo
    -0.71
    velocityX
    -0.69
    guigu
    -0.69
    POSITIVE LOGITS
     SEO
    1.73
     CMS
    1.59
     content
    1.59
     banner
    1.50
     news
    1.47
    cms
    1.47
    SEO
    1.47
     banners
    1.44
     cms
    1.43
    Cms
    1.35
    Activations Density 0.016%

    No Known Activations