© 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. 101987
    Prev
    Next
    INDEX
    Explanations

    business and technical terms

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

    abbreviated organizational or technical terms, particularly alphanumeric codes and acronyms in formal or academic contexts.

    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
     pittores
    -1.66
     maniere
    -1.57
     مجموعة
    -1.52
    茕
    -1.50
     réve
    -1.50
     idyl
    -1.50
     ſa
    -1.49
    趿
    -1.48
     individuelles
    -1.47
     kiti
    -1.47
    POSITIVE LOGITS
     at
    2.66
     three
    2.48
     two
    2.38
     only
    2.38
     four
    2.25
     their
    2.22
     very
    2.19
     during
    2.17
     until
    2.16
     before
    2.14
    Activations Density 0.263%

    No Known Activations