© 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-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 7764
    Prev
    Next
    INDEX
    Explanations

    win or 2-1

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    िंग
    1.16
     Informasi
    1.09
    Ң
    1.04
    Н
    1.02
     excitedly
    1.00
    ש
    0.99
     Öffentlichkeit
    0.97
    あるいは
    0.97
    ज़
    0.96
     amused
    0.96
    POSITIVE LOGITS
    1.04
    ло
    1.01
    ის
    0.95
     is
    0.93
    ভাবে
    0.90
     y
    0.88
    ه
    0.88
    மாக
    0.88
     permite
    0.88
    uing
    0.86
    Activations Density 0.030%

    No Known Activations