© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 9133
    Prev
    Next
    INDEX
    Explanations

    electronic or online items

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

    digital, online, electronic services

    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_262k_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
    ação
    0.48
    国道
    0.44
     klinik
    0.44
    ſe
    0.43
    在
    0.43
    ின்
    0.43
    اك
    0.43
     제도
    0.43
    的
    0.42
    យើង
    0.42
    POSITIVE LOGITS
    c
    0.64
     electronic
    0.62
     Electronic
    0.62
    electronic
    0.59
     Online
    0.54
     Digital
    0.52
     online
    0.52
     digital
    0.49
    Electronic
    0.49
     Virtual
    0.48
    Activations Density 0.112%

    No Known Activations