© 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-16K
    7. 7630
    Prev
    Next
    INDEX
    Explanations

    DIY decor options

    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_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
    iono
    0.66
    unctive
    0.64
     ativar
    0.63
     değiş
    0.63
    Infrastructure
    0.63
    ACTIVE
    0.62
    密钥
    0.62
    臻
    0.62
    と共に
    0.61
    phenylsulfanyl
    0.61
    POSITIVE LOGITS
     homemade
    1.96
     DIY
    1.77
     Homemade
    1.74
    DIY
    1.72
    Homemade
    1.68
    homemade
    1.66
     bought
    1.50
     Ebay
    1.49
     improvised
    1.47
     ebay
    1.47
    Activations Density 0.536%

    No Known Activations