© 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. 219518
    Prev
    Next
    INDEX
    Explanations

    US-facing operators

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

    including or excluding details

    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
    瑶
    0.48
     typology
    0.45
    Referring
    0.44
     Parma
    0.43
     kolom
    0.43
     L
    0.43
    础
    0.43
    对方
    0.42
    编制
    0.42
    Fram
    0.42
    POSITIVE LOGITS
    ບໍ່
    0.49
     ພວກເຮົາ
    0.48
     prefque
    0.47
     вам
    0.46
     দেহের
    0.46
    យើង
    0.46
     ''){
    0.45
     এলিট
    0.45
     bạn
    0.45
    pixel
    0.45
    Activations Density 0.001%

    No Known Activations