© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 6987
    Prev
    Next
    INDEX
    Explanations

    tonight's forecast

    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_262k_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
    ⺆
    1.77
    되었다
    1.23
    ようになった
    1.23
    てください
    1.20
    在了
    1.20
    りたい
    1.18
     الإنترنت
    1.17
     перший
    1.16
    끝
    1.15
     गौरतलब
    1.14
    POSITIVE LOGITS
    ,
    1.17
    ↵
    1.09
    br
    1.02
    ल
    1.00
     hùng
    1.00
    ،
    0.98
    ں
    0.95
    σης
    0.92
    lx
    0.91
     morceaux
    0.91
    Activations Density 0.003%

    No Known Activations