© 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. 10-GEMMASCOPE-RES-131K
    7. 103729
    Prev
    Next
    INDEX
    Explanations

    structured data formats

    np_acts-logits-general · gemini-2.5-flash-lite

    closing brackets or braces in structured data like arrays, lists, or JSON objects within code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    </h3>
    -2.00
    Through
    -1.89
    </sub>
    -1.87
    M
    -1.77
                            
    -1.74
    從
    -1.74
    Since
    -1.72
     الذي
    -1.66
    Though
    -1.65
    From
    -1.63
    POSITIVE LOGITS
     destacan
    1.90
     diverso
    1.75
    regalo
    1.70
     proporcionan
    1.70
     vieler
    1.64
     Anſ
    1.63
     paisajes
    1.63
    
    1.63
    驺
    1.62
     devised
    1.60
    Activations Density 0.010%

    No Known Activations