© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-16K
    4. 863
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     phút
    2.20
     marvelous
    2.05
    ปลอดภัย
    1.92
     pamoja
    1.91
     poiché
    1.88
    այի
    1.86
    𝑝
    1.85
     marvellous
    1.82
    Analyser
    1.82
    玧
    1.80
    POSITIVE LOGITS
     Pals
    2.98
     Picks
    2.30
    礴
    2.09
     Penh
    2.05
    靂
    2.05
     پیغمبر
    2.03
    Pc
    2.02
     Pantry
    2.00
     Pilgr
    1.95
     étudi
    1.94
    Activations Density 4.160%

    No Known Activations