© 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. 35023
    Prev
    Next
    INDEX
    Explanations

    completing safety

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

    purpose or process explanation

    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
     şimdi
    0.67
     يا
    0.60
     için
    0.57
    leyeceğiz
    0.57
     konte
    0.55
     iki
    0.54
     bağ
    0.54
    为
    0.54
     veya
    0.53
     bunu
    0.53
    POSITIVE LOGITS
     climatic
    0.72
     diversified
    0.67
     materialistic
    0.66
     sufferings
    0.64
     imparting
    0.62
     topmost
    0.62
     reputed
    0.62
     irrespective
    0.61
     wastage
    0.61
     futuristic
    0.60
    Activations Density 0.346%

    No Known Activations