© 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. 499
    Prev
    Next
    INDEX
    Explanations

    emits light and related phenomena

    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
     jego
    -1.22
    ᾖ
    -1.18
    
    -1.17
    笵
    -1.16
     brilla
    -1.16
     parlement
    -1.16
     simpat
    -1.14
     totalt
    -1.13
    部分を
    -1.13
    部分が
    -1.13
    POSITIVE LOGITS
     a
    2.47
     both
    1.91
     an
    1.86
     enough
    1.52
     sufficient
    1.48
     more
    1.48
     some
    1.47
     myös
    1.43
     enormous
    1.43
     such
    1.42
    Activations Density 0.089%

    No Known Activations