© 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. 24-GEMMASCOPE-2-RES-16K
    7. 6043
    Prev
    Next
    INDEX
    Explanations

    fractions or divisions

    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_24_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
    ur
    0.65
    new
    0.60
    pppp
    0.57
    ck
    0.57
    social
    0.55
    4
    0.55
    Game
    0.54
    ne
    0.54
    https
    0.54
    ウ
    0.54
    POSITIVE LOGITS
     Cumm
    0.62
    糉
    0.62
     Maastricht
    0.61
     Admittedly
    0.59
     ничек
    0.58
     ඉතා
    0.58
     Secondly
    0.57
     Ideally
    0.57
     প্রথমেই
    0.57
     Kull
    0.56
    Activations Density 0.001%

    No Known Activations