© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 568
    Prev
    Next
    INDEX
    Explanations

    in the meantime

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_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
    の
    0.52
    의
    0.52
    的
    0.50
    ﺎ
    0.48
     的
    0.47
    ᅴ
    0.46
     의
    0.45
     فى
    0.45
     Сайт
    0.44
     ಮತ್ತು
    0.43
    POSITIVE LOGITS
     midst
    1.22
     vicinity
    1.05
     meantime
    0.98
     absence
    0.91
     guise
    0.88
     realm
    0.85
     context
    0.84
     wake
    0.84
     aftermath
    0.82
     middle
    0.75
    Activations Density 1.043%

    No Known Activations