© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 752
    Prev
    Next
    INDEX
    Explanations

    directing focus or interest

    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_53_width_65k_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
    для
    0.31
     บน
    0.29
    บน
    0.29
     করিয়৷
    0.28
    เกี่ยวกับ
    0.27
     trên
    0.27
     pada
    0.27
    關於
    0.26
     для
    0.26
     روی
    0.25
    POSITIVE LOGITS
    䏹
    0.37
     zarówno
    0.33
     solely
    0.28
    (?)
    0.28
     (?)
    0.27
    <unused2197>
    0.27
     xhrObj
    0.26
     wt
    0.26
     sowohl
    0.26
     vaan
    0.25
    Activations Density 3.851%

    No Known Activations