© 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. 34-GEMMASCOPE-RES-131K
    7. 34571
    Prev
    Next
    INDEX
    Explanations

    determiner adjective

    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_34/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
     different
    -1.58
     diferentes
    -1.54
    different
    -1.34
    色々な
    -1.33
     rekan
    -1.28
     Wirken
    -1.26
     圖片
    -1.23
     différents
    -1.20
     changes
    -1.16
     africaine
    -1.16
    POSITIVE LOGITS
     jit
    1.22
     equally
    1.21
     impos
    1.19
     manifestly
    1.16
     dourada
    1.15
     airy
    1.13
     eneste
    1.13
     infinitely
    1.11
     cant
    1.11
     altogether
    1.10
    Activations Density 0.141%

    No Known Activations