Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-16K
    4. 3084
    Prev
    Next
    INDEX
    Explanations

    Rigid

    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
     humanist
    1.20
    ⓓ
    1.07
    ագր
    1.04
     Hebre
    1.03
     Dutta
    1.00
     ছুই
    1.00
    ции
    0.98
     Mandalorian
    0.98
    聸
    0.98
    糖尿
    0.98
    POSITIVE LOGITS
    ్‌
    1.48
    ul
    1.23
    一场
    1.23
    ो
    1.13
    uring
    1.09
    ไม่ใช่
    1.09
    同时
    1.07
    ানা
    1.05
    ηση
    1.00
    ikala
    0.99
    Activations Density 0.003%

    No Known Activations