© 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. 54439
    Prev
    Next
    INDEX
    Explanations

    temporal change and comparisons

    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
    midler
    -1.16
     blessure
    -1.16
     hablado
    -1.13
     الشرطة
    -1.13
     llamaba
    -1.12
    ׇ
    -1.12
     بیمارستان
    -1.11
     tragé
    -1.10
    ashqai
    -1.09
    ༻
    -1.09
    POSITIVE LOGITS
     last
    1.52
     this
    1.46
     these
    1.45
     it
    1.35
    ,
    1.23
    ֶּ
    1.13
     previous
    1.09
     compared
    1.09
     average
    1.08
     latest
    1.04
    Activations Density 0.024%

    No Known Activations