© 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. 2772
    Prev
    Next
    INDEX
    Explanations

    enjoying talking and expressing

    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
    ру
    1.48
    к
    1.43
    Μ
    1.26
    Breath
    1.25
    ре
    1.23
     इरा
    1.21
    ।
    1.20
    А
    1.20
    Ве
    1.17
     Много
    1.17
    POSITIVE LOGITS
     pastime
    1.69
    ا
    1.55
    乐趣
    1.47
    nies
    1.45
    ıma
    1.37
    ına
    1.35
    ującego
    1.35
    ı
    1.35
    ni
    1.34
     festivities
    1.33
    Activations Density 0.679%

    No Known Activations