© 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. 22-GEMMASCOPE-RES-131K
    7. 95330
    Prev
    Next
    INDEX
    Explanations

    numbers before or after specific words

    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
     plafon
    -1.77
     faciliter
    -1.68
     dát
    -1.64
     siè
    -1.64
     très
    -1.58
    ఽ
    -1.58
     maniere
    -1.57
     constater
    -1.55
     corriger
    -1.55
     charmant
    -1.53
    POSITIVE LOGITS
     eight
    1.97
     three
    1.89
     five
    1.87
     not
    1.86
     seven
    1.84
     getting
    1.80
     even
    1.78
     can
    1.77
     on
    1.77
     If
    1.76
    Activations Density 0.445%

    No Known Activations