© 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. 7526
    Prev
    Next
    INDEX
    Explanations

    foreign technical terms and names

    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
    ті
    2.30
    ви
    2.19
    ുന്ന
    2.13
    са
    2.06
    ז
    2.06
    ൂ
    2.03
    ung
    2.00
    ن
    1.96
    ously
    1.93
    ्
    1.93
    POSITIVE LOGITS
     অপরের
    2.27
    keits
    2.16
    ्रेडिट
    2.11
    ल्याण
    2.09
    至于
    1.98
     ОК
    1.95
    ын
    1.91
    itekt
    1.91
    ழ்பெற்ற
    1.89
     Tecn
    1.88
    Activations Density 0.363%

    No Known Activations