© 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. 37035
    Prev
    Next
    INDEX
    Explanations

    money advance or earn money

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

    Hong Kong, jellyfish, event, frequent

    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
    ćem
    0.56
    ྃ
    0.52
     Frederik
    0.49
     Frederic
    0.48
    ਣ
    0.48
    ੁਰ
    0.48
    ི་
    0.47
     procesu
    0.47
     basilica
    0.47
    ਮੀ
    0.46
    POSITIVE LOGITS
     español
    0.45
     प्रव
    0.45
    l
    0.42
    extended
    0.42
    iforn
    0.42
     puts
    0.41
     بسر
    0.41
    o
    0.41
     formato
    0.41
    gcj
    0.41
    Activations Density 0.000%

    No Known Activations