© 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. 12273
    Prev
    Next
    INDEX
    Explanations

    for specific items

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

    purpose or situation context

    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
    لام
    0.37
    อร์
    0.37
    女の子
    0.37
    إ
    0.35
    লা
    0.34
    两天
    0.34
    ementerian
    0.34
    irmed
    0.34
    اپ
    0.34
    
    0.33
    POSITIVE LOGITS
     casos
    0.49
     przypadku
    0.49
     situations
    0.46
     لاءِ
    0.46
     cases
    0.45
     შემთხვევაში
    0.44
     ترلاسه
    0.40
     случаи
    0.39
     qPCR
    0.39
     angios
    0.39
    Activations Density 0.021%

    No Known Activations