© 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-262K
    4. 68
    Prev
    Next
    INDEX
    Explanations

    sustainable development, living, energy, harvesting

    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_262k_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
    م
    1.71
    м
    1.47
    ко
    1.41
    是由
    1.39
    ર
    1.32
    ет
    1.30
    ჯგუფი
    1.30
    (\
    1.27
    кому
    1.23
    ح
    1.23
    POSITIVE LOGITS
    नंतर
    1.41
    ía
    1.25
    দীর্ঘ
    1.23
     Branco
    1.22
     dược
    1.20
     pasando
    1.19
     Trebuie
    1.17
     chỗ
    1.16
     czyli
    1.15
     Sá
    1.15
    Activations Density 0.006%

    No Known Activations