© 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-65K
    7. 2538
    Prev
    Next
    INDEX
    Explanations

    Dr. Michael Gray

    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_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
    為主
    1.17
    龧
    1.09
     multilateral
    1.08
    𒌷
    1.07
     ব্যাকটেরিয়া
    1.07
    marshalN
    1.07
     governs
    1.06
     核
    1.06
    がありますが
    1.06
    𒁹
    1.06
    POSITIVE LOGITS
     unbelievably
    1.87
    !!!!
    1.70
    !!!
    1.69
    !!!!!!
    1.66
    !!!!!!!
    1.64
    Needless
    1.63
     Needless
    1.63
    !!!!!!!!
    1.62
    !!!!!
    1.58
    !!
    1.55
    Activations Density 1.227%

    No Known Activations