© 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. 10-GEMMASCOPE-RES-131K
    7. 41337
    Prev
    Next
    INDEX
    Explanations

    testing keywords and code constructs

    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_10/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
     obf
    -1.40
     ↔
    -1.38
     igr
    -1.36
     primeiros
    -1.34
     occidentale
    -1.34
    valuable
    -1.34
     bricolaje
    -1.33
    λία
    -1.32
     itp
    -1.32
    Välisling
    -1.31
    POSITIVE LOGITS
     Some
    1.55
     will
    1.41
    ↵
    1.38
     Neither
    1.37
     might
    1.36
        
    1.34
     Having
    1.33
    }
    1.32
     Nearly
    1.31
     Trying
    1.31
    Activations Density 0.043%

    No Known Activations