© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 7768
    Prev
    Next
    INDEX
    Explanations

    XOR operator

    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_13_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
    en
    2.53
    ে
    2.52
    y
    2.47
    yana
    2.47
    ン
    2.45
    eniz
    2.44
    yı
    2.38
    yó
    2.35
    iest
    2.33
    iin
    2.28
    POSITIVE LOGITS
    逅
    2.35
    Eh
    2.28
    𝓲
    2.28
     Seesaw
    2.28
    พย์
    2.27
    𝓾
    2.26
    𝟘
    2.26
    itioner
    2.23
    𝘂
    2.22
    intValue
    2.20
    Activations Density 0.083%

    No Known Activations