© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 1630
    Prev
    Next
    INDEX
    Explanations

    subtract, eliminate, inverse, swap

    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
    DEPTH
    1.61
    蔔
    1.54
    uerre
    1.49
     फ्लाइट
    1.48
    dfunding
    1.48
    𝐬
    1.47
    Registration
    1.46
    Optimization
    1.46
    জাতি
    1.45
     SIR
    1.45
    POSITIVE LOGITS
     tuli
    1.47
    a
    1.34
     đ
    1.34
     pô
    1.29
    ו
    1.29
    /−
    1.28
    ா
    1.24
     keç
    1.19
     पौ
    1.19
    ią
    1.17
    Activations Density 0.000%

    No Known Activations