© 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-3-12B-IT
    5. 41-GEMMASCOPE-2-RES-16K
    7. 7059
    Prev
    Next
    INDEX
    Explanations

    LangChain framework

    np_max-act-logits · gemini-2.5-flash-lite

    exquisite style pairing

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_41_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
     паліты
    0.73
     सूचना
    0.68
     পরীক্ষা
    0.66
     política
    0.65
     Vos
    0.63
     político
    0.59
    }}=-\
    0.59
     জীবিত
    0.58
     eviction
    0.58
     politika
    0.57
    POSITIVE LOGITS
    搭配
    0.89
     exquis
    0.82
     exquisite
    0.79
    美食
    0.74
    精致
    0.72
    打造
    0.71
    特色
    0.71
    媲
    0.69
    气质
    0.69
    配
    0.69
    Activations Density 0.068%

    No Known Activations