© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27164
    Prev
    Next
    INDEX
    Explanations

    artists and their artworks

    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_22/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
     recommended
    -1.15
     móg
    -1.06
     shouldn
    -1.04
    ּוֹ
    -1.04
     good
    -1.03
     should
    -1.02
    ְּ
    -1.02
    B
    -1.02
    有助
    -1.02
    實際
    -0.98
    POSITIVE LOGITS
     creation
    1.23
    moveToNext
    1.22
     vegetales
    1.22
    
    1.20
    materials
    1.20
    курс
    1.20
     projektu
    1.20
     projects
    1.19
    Ý
    1.18
     ὑ
    1.15
    Activations Density 0.047%

    No Known Activations