© 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. 1286
    Prev
    Next
    INDEX
    Explanations

    light novel, light-hearted, lighter fare

    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
    皷
    -1.36
    ?
    -1.33
     where
    -1.31
     després
    -1.30
    籏
    -1.29
    人的
    -1.28
     piccole
    -1.20
     diversos
    -1.20
     trabajan
    -1.19
    それは
    -1.18
    POSITIVE LOGITS
    Rumah
    1.35
    Memoria
    1.23
    Fitur
    1.21
    Teilen
    1.21
     Light
    1.20
    你喜欢
    1.20
    Teknik
    1.20
    Makan
    1.19
    distrito
    1.19
    Maka
    1.17
    Activations Density 0.029%

    No Known Activations