© 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. 10-GEMMASCOPE-RES-131K
    7. 1252
    Prev
    Next
    INDEX
    Explanations

    SIP, DTC, tmpl, eli

    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_10/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
    棪
    -3.02
     戰
    -3.00
    ⬮
    -2.75
     來
    -2.64
    Дети
    -2.61
    瓩
    -2.59
     與
    -2.58
    Кто
    -2.56
     味噌
    -2.55
     faldas
    -2.55
    POSITIVE LOGITS
     dando
    2.75
     
    2.72
     we
    2.64
     '
    2.58
     Our
    2.58
    亖
    2.44
    はどう
    2.38
    縢
    2.33
                    
    2.28
     "
    2.28
    Activations Density 0.005%

    No Known Activations