© 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. 42340
    Prev
    Next
    INDEX
    Explanations

    conferences and events

    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
    使用
    -1.39
    也有
    -1.34
    其他
    -1.33
     wykor
    -1.32
     illustratie
    -1.26
     due
    -1.25
     utilizar
    -1.24
    eight
    -1.23
    ep
    -1.22
    5
    -1.22
    POSITIVE LOGITS
     always
    1.25
    capulco
    1.21
     annuelle
    1.17
     marts
    1.14
    lighed
    1.14
     brasileira
    1.14
     commod
    1.13
    ㌘
    1.13
    madeus
    1.12
     annuel
    1.11
    Activations Density 0.130%

    No Known Activations