© 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. 54292
    Prev
    Next
    INDEX
    Explanations

    us or we

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

    programming code keywords

    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
    必
    0.45
    ('
    0.41
    Tablet
    0.37
    [&
    0.37
     Nodes
    0.36
     fib
    0.36
     你
    0.36
    日程
    0.35
    节点
    0.35
    节点的
    0.35
    POSITIVE LOGITS
    ramos
    0.52
     nossa
    0.52
     نحن
    0.50
    lerimiz
    0.50
     nuestra
    0.47
     करतो
    0.47
     podamos
    0.46
     kaldığımız
    0.46
    uyoruz
    0.46
     sentimos
    0.46
    Activations Density 0.000%

    No Known Activations