© 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. 12605
    Prev
    Next
    INDEX
    Explanations

    source filename or code

    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
     线条
    -1.60
    
    -1.48
    骉
    -1.48
     picioare
    -1.43
     配件
    -1.41
     fiabilidad
    -1.41
     cúp
    -1.39
     厂家
    -1.38
    präch
    -1.36
    采用了
    -1.36
    POSITIVE LOGITS
     will
    2.17
    )
    2.09
     has
    1.96
    3
    1.67
    9
    1.65
    ;
    1.55
     July
    1.53
     more
    1.52
    :
    1.52
     should
    1.47
    Activations Density 0.000%

    No Known Activations