© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-16K
    4. 13582
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    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
    儡
    1.83
     multiplicities
    1.67
    みました
    1.62
    ic
    1.57
    っきり
    1.57
    しないで
    1.57
     подхода
    1.55
    ').
    1.54
    いる
    1.54
    出典
    1.54
    POSITIVE LOGITS
     folos
    2.19
    깐
    2.05
    ло
    2.02
     všet
    1.98
     perfectamente
    1.98
    스는
    1.98
    ми
    1.91
    你
    1.91
    и
    1.90
     ทำ
    1.89
    Activations Density 0.116%

    No Known Activations