© 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. 6858
    Prev
    Next
    INDEX
    Explanations

    comment syntax

    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
    s
    2.28
    ot
    2.23
    el
    2.22
    ar
    2.14
    od
    2.05
    et
    1.98
    ir
    1.95
    al
    1.94
    ad
    1.94
    ↵
    1.92
    POSITIVE LOGITS
    𝐫
    2.08
    𝐓
    1.93
    യിൽ
    1.92
    𝑵
    1.88
    𝐍
    1.87
    𝐖
    1.80
    𝖒
    1.78
    ᚨ
    1.78
    𝗆
    1.77
    𝐑
    1.77
    Activations Density 0.100%

    No Known Activations