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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 24-GEMMASCOPE-2-RES-16K
    4. 105
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_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
    才可以
    0.18
    ʿ
    0.18
     посредством
    0.18
     gravedad
    0.17
     zucchero
    0.17
     alcuna
    0.17
    ້ອ
    0.16
     reptiles
    0.16
     aient
    0.16
    และความ
    0.16
    POSITIVE LOGITS
    :
    0.35
    :
    0.30
     utama
    0.30
    例子
    0.27
    特点
    0.26
     :
    0.26
     Notable
    0.26
     notable
    0.26
    ঃ
    0.26
     noteworthy
    0.25
    Activations Density 8.857%

    No Known Activations