© 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. 6106
    Prev
    Next
    INDEX
    Explanations

    "`"

    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
     Additionally
    0.58
    2
    0.58
    4
    0.57
    د
    0.52
    9
    0.51
     Mindfulness
    0.51
     Washington
    0.50
    7
    0.50
     USAID
    0.50
    1
    0.50
    POSITIVE LOGITS
    crossentropy
    0.57
    ເຂົ້າ
    0.49
    時間を
    0.48
    পক্ষে
    0.46
     ceas
    0.46
     occasion
    0.45
     никаких
    0.45
     suppuration
    0.45
    すべき
    0.45
     `--
    0.44
    Activations Density 0.000%

    No Known Activations