© 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
    3. Gemma-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15690
    Prev
    Next
    INDEX
    Explanations

    Day 1:

    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_31_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
     pela
    0.83
     oleh
    0.77
     dengan
    0.75
     Throughout
    0.74
     melalui
    0.70
     tanpa
    0.69
     첫
    0.69
     với
    0.66
     seu
    0.66
     pertama
    0.66
    POSITIVE LOGITS
    তুমি
    0.62
     везде
    0.52
     լ
    0.49
    <unused12>
    0.48
    termination
    0.48
    QT
    0.47
    Marketing
    0.47
    塞
    0.47
    ackbar
    0.47
    antiation
    0.47
    Activations Density 0.047%

    No Known Activations