© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11982
    Prev
    Next
    INDEX
    Explanations

    base64 encoding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_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
     當
    2.10
     ‍
    2.09
    𐰃
    2.07
     啊
    2.06
    𐱃
    2.03
     單
    2.00
     핵심
    1.98
    𐰆
    1.97
     bình
    1.95
     irons
    1.95
    POSITIVE LOGITS
    ed
    1.42
    ing
    1.41
    ado
    1.38
    news
    1.35
    ador
    1.31
    na
    1.30
    s
    1.28
    ng
    1.22
    Vice
    1.21
    ting
    1.20
    Activations Density 0.006%

    No Known Activations