© 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. 130132
    Prev
    Next
    INDEX
    Explanations

    programming keywords and 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_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
     their
    -2.38
     even
    -1.99
     people
    -1.89
     by
    -1.86
     from
    -1.80
     like
    -1.74
     all
    -1.73
     at
    -1.66
     more
    -1.63
     there
    -1.53
    POSITIVE LOGITS
     trám
    1.63
    튿
    1.54
    趼
    1.46
     AMAZING
    1.41
    Continua
    1.40
    
    1.39
     ซึ่ง
    1.38
     VERY
    1.37
    urably
    1.37
    Ingredienti
    1.35
    Activations Density 0.002%

    No Known Activations