© 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. 79647
    Prev
    Next
    INDEX
    Explanations

    more than

    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
     then
    -1.96
     लेकिन
    -1.18
     therefore
    -1.18
     when
    -1.16
     Then
    -1.16
     subsequently
    -1.16
     consequently
    -1.02
    而又
    -1.02
     But
    -1.00
     akhirnya
    -1.00
    POSITIVE LOGITS
     invece
    1.30
     гораздо
    1.16
     basé
    1.11
     більш
    1.11
     наоборот
    1.09
    のほうが
    1.07
     daha
    1.04
     more
    1.03
    llllll
    1.02
    lllllll
    1.01
    Activations Density 0.054%

    No Known Activations