© 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. 14635
    Prev
    Next
    INDEX
    Explanations

    artificial intelligence and machine learning

    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
     ovvero
    1.23
    ř
    1.22
     pesawat
    1.18
     jogo
    1.17
     umfang
    1.16
     instruções
    1.14
     muut
    1.13
    ılabilir
    1.13
     alemão
    1.13
    र
    1.13
    POSITIVE LOGITS
    Стра
    1.26
    HERE
    1.24
    वंश
    1.16
    AG
    1.13
    Mz
    1.13
    EDUCATION
    1.10
    émica
    1.09
    我去
    1.07
    CUDA
    1.06
    ције
    1.05
    Activations Density 0.296%

    No Known Activations