© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 5104
    Prev
    Next
    INDEX
    Explanations

    quotes and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_65k_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
    ()=>{
    3.04
    𝚘
    2.01
    𝚣
    1.95
    𝚜
    1.94
    𝚞
    1.88
    𝚋
    1.80
    𝚢
    1.77
    𝚐
    1.76
    𝚔
    1.76
    𝚊
    1.67
    POSITIVE LOGITS
    Tis
    2.11
    ia
    1.79
    ă
    1.66
    й
    1.62
    "",
    1.56
    -->'
    1.54
     '*
    1.54
    ...'
    1.52
    ra
    1.50
    "%
    1.47
    Activations Density 0.232%

    No Known Activations