© 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. 7326
    Prev
    Next
    INDEX
    Explanations

    equal opportunities

    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
     decidedly
    1.36
     captivating
    1.28
     assorted
    1.26
    ®
    1.21
     incredibly
    1.18
     seemingly
    1.15
     throughout
    1.14
     delightfully
    1.14
     continual
    1.09
     ubiquitous
    1.09
    POSITIVE LOGITS
     lazım
    1.59
     треба
    1.58
     догово
    1.57
     надо
    1.55
     ডেভেলপ
    1.53
    ㇇
    1.50
     fizemos
    1.50
     不能
    1.49
     مشکلات
    1.44
     tivemos
    1.43
    Activations Density 0.033%

    No Known Activations