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. 12-GEMMASCOPE-2-RES-16K
    4. 2352
    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_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
    SSSS
    1.75
     SULF
    1.63
     affectionately
    1.62
    𝘦
    1.61
    esque
    1.57
    n
    1.55
    ICLE
    1.55
    et
    1.53
     Whoever
    1.52
    PASS
    1.51
    POSITIVE LOGITS
    나
    1.99
    ود
    1.90
    да
    1.84
    ет
    1.78
    हून
    1.77
    ている
    1.71
    ↵
    1.70
    шло
    1.63
    ર
    1.63
    化
    1.61
    Activations Density 0.861%

    No Known Activations