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. 2548
    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
    ம்
    2.27
    ある
    2.17
    出色
    2.17
    ான்
    2.11
    able
    2.06
    м
    2.03
    い
    2.00
    ST
    1.91
    ل
    1.90
    LLS
    1.89
    POSITIVE LOGITS
    s
    1.91
    tingham
    1.84
    Еще
    1.81
    tų
    1.80
     않으면
    1.80
    নীতি
    1.77
     возможность
    1.74
    termilk
    1.74
    ted
    1.72
     financieras
    1.71
    Activations Density 0.366%

    No Known Activations