© 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
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 14818
    Prev
    Next
    INDEX
    Explanations

    expert roles and services

    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
    erde
    2.05
    ز
    1.98
    但是我
    1.80
    涯
    1.80
     entrepreneur
    1.79
    erte
    1.76
     wayside
    1.75
     ingenuity
    1.74
    Y
    1.74
    مو
    1.72
    POSITIVE LOGITS
    ן
    2.27
    і
    2.08
     sendo
    1.85
    𝑜
    1.85
    но
    1.83
    р
    1.77
    enfants
    1.76
     pasando
    1.75
     cuarent
    1.73
    于是
    1.67
    Activations Density 0.024%

    No Known Activations