© 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. 25853
    Prev
    Next
    INDEX
    Explanations

    parks in

    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
    大量的
    -1.27
     our
    -1.26
     Touristen
    -1.18
     כאשר
    -1.09
    fasterxml
    -1.09
     fuckin
    -1.06
    bilecek
    -1.05
    มากๆ
    -1.05
     berichtet
    -1.02
    asantry
    -1.02
    POSITIVE LOGITS
     pret
    1.10
    بیر
    1.07
     rewarding
    1.05
    СИ
    1.03
    ПО
    1.03
    ╹
    1.02
    奖励
    1.01
    骄傲
    1.00
     moo
    1.00
    يع
    1.00
    Activations Density 0.073%

    No Known Activations