© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15939
    Prev
    Next
    INDEX
    Explanations

    Vive, cubes, services, legitimate, biggest

    np_acts-logits-general · gemini-2.5-flash-lite

    I describing self or difference

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     clo
    0.50
     bulund
    0.48
    ни
    0.47
     nhiên
    0.47
     hyd
    0.46
     తర్వాత
    0.45
    ?
    0.44
    解释
    0.44
     pét
    0.44
    后面的
    0.44
    POSITIVE LOGITS
    안녕하세요
    0.49
    碐
    0.49
    ിയുടെ
    0.48
     വേദ
    0.46
     Freude
    0.45
    𝘔
    0.45
     penggem
    0.44
    মা
    0.44
     synes
    0.44
    していますが
    0.44
    Activations Density 0.037%

    No Known Activations