© 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. 72495
    Prev
    Next
    INDEX
    Explanations

    electronic commerce

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

    tokens vs. words

    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
     욕
    0.58
     Два
    0.57
     стрем
    0.55
    ISATION
    0.54
     ต้องการ
    0.53
     хочу
    0.52
     nostre
    0.52
     creciente
    0.52
     फाउंडेशन
    0.51
     विवाह
    0.51
    POSITIVE LOGITS
     remotely
    0.47
    ood
    0.46
    date
    0.45
     date
    0.44
     distribute
    0.43
    0
    0.43
     electronic
    0.43
     electronically
    0.43
     fleet
    0.42
     distributes
    0.42
    Activations Density 0.002%

    No Known Activations