© 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. 15022
    Prev
    Next
    INDEX
    Explanations

    obtain information

    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
     وفي
    2.06
    于
    1.93
    ell
    1.76
    ราว
    1.63
     leveling
    1.60
    imize
    1.59
    ulièrement
    1.59
    也没
    1.58
     dennoch
    1.58
    ृती
    1.58
    POSITIVE LOGITS
    га
    2.66
    на
    2.47
    лна
    2.27
    тата
    2.13
    تها
    2.05
    лган
    2.03
    т
    2.03
    ત
    1.97
    تين
    1.95
    ו
    1.95
    Activations Density 0.038%

    No Known Activations