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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130563
    Prev
    Next
    INDEX
    Explanations

    research and technology collaboration

    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
    ureusement
    -1.56
    ないです
    -1.37
     appris
    -1.34
    Ikke
    -1.33
    ค่ะ
    -1.32
    mejores
    -1.29
     hidratante
    -1.27
    PUESTA
    -1.27
    ämme
    -1.24
     Komunikasi
    -1.23
    POSITIVE LOGITS
     research
    1.61
     metus
    1.50
     projects
    1.44
     capabilities
    1.38
     technologies
    1.29
    踔
    1.29
     scientists
    1.23
    gtest
    1.22
    matlab
    1.20
     technology
    1.20
    Activations Density 0.068%

    No Known Activations